Guangming Wang

Guangming Wang, Yunzhe Hu, Zhe Liu et al.

3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames. Thus, it is critical for the flow embeddings to capture the correct overall direction of the motion. However, previous works only search locally to determine a soft correspondence, ignoring the distant points that turn out to be the actual matching ones. In addition, the estimated correspondence is usually from the forward direction of the adjacent point clouds, and may not be consistent with the estimated correspondence acquired from the backward direction. To tackle these problems, we propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Besides, we investigate and compare several design choices in key components of the 3D scene flow network, including the point similarity calculation, input elements of predictor, and predictor & refinement level design. After carefully choosing the most effective designs, we are able to present a model that achieves the state-of-the-art performance on FlyingThings3D and KITTI Scene Flow datasets. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric. We release our codes at https://github.com/IRMVLab/3DFlow.

Guangming Wang, Yu Zheng, Yuxuan Wu et al.

Robot localization using a built map is essential for a variety of tasks including accurate navigation and mobile manipulation. A popular approach to robot localization is based on image-to-point cloud registration, which combines illumination-invariant LiDAR-based mapping with economical image-based localization. However, the recent works for image-to-point cloud registration either divide the registration into separate modules or project the point cloud to the depth image to register the RGB and depth images. In this paper, we present I2PNet, a novel end-to-end 2D-3D registration network, which directly registers the raw 3D point cloud with the 2D RGB image using differential modules with a united target. The 2D-3D cost volume module for differential 2D-3D association is proposed to bridge feature extraction and pose regression. The soft point-to-pixel correspondence is implicitly constructed on the intrinsic-independent normalized plane in the 2D-3D cost volume module. Moreover, we introduce an outlier mask prediction module to filter the outliers in the 2D-3D association before pose regression. Furthermore, we propose the coarse-to-fine 2D-3D registration architecture to increase localization accuracy. Extensive localization experiments are conducted on the KITTI, nuScenes, M2DGR, Argoverse, Waymo, and Lyft5 datasets. The results demonstrate that I2PNet outperforms the state-of-the-art by a large margin and has a higher efficiency than the previous works. Moreover, we extend the application of I2PNet to the camera-LiDAR online calibration and demonstrate that I2PNet outperforms recent approaches on the online calibration task. Source codes are released at https://github.com/IRMVLab/I2PNet.

Chensheng Peng, Guangming Wang, Xian Wan Lo et al. · berkeley

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset.

Chang Nie, Guangming Wang, Zhe Liu et al.

Robust estimation is a crucial and still challenging task, which involves estimating model parameters in noisy environments. Although conventional sampling consensus-based algorithms sample several times to achieve robustness, these algorithms cannot use data features and historical information effectively. In this paper, we propose RLSAC, a novel Reinforcement Learning enhanced SAmple Consensus framework for end-to-end robust estimation. RLSAC employs a graph neural network to utilize both data and memory features to guide exploring directions for sampling the next minimum set. The feedback of downstream tasks serves as the reward for unsupervised training. Therefore, RLSAC can avoid differentiating to learn the features and the feedback of downstream tasks for end-to-end robust estimation. In addition, RLSAC integrates a state transition module that encodes both data and memory features. Our experimental results demonstrate that RLSAC can learn from features to gradually explore a better hypothesis. Through analysis, it is apparent that RLSAC can be easily transferred to other sampling consensus-based robust estimation tasks. To the best of our knowledge, RLSAC is also the first method that uses reinforcement learning to sample consensus for end-to-end robust estimation. We release our codes at https://github.com/IRMVLab/RLSAC.

Huixin Zhang, Guangming Wang, Xinrui Wu et al.

This paper introduces a 3D point cloud sequence learning model based on inconsistent spatio-temporal propagation for LiDAR odometry, termed DSLO. It consists of a pyramid structure with a spatial information reuse strategy, a sequential pose initialization module, a gated hierarchical pose refinement module, and a temporal feature propagation module. First, spatial features are encoded using a point feature pyramid, with features reused in successive pose estimations to reduce computational overhead. Second, a sequential pose initialization method is introduced, leveraging the high-frequency sampling characteristic of LiDAR to initialize the LiDAR pose. Then, a gated hierarchical pose refinement mechanism refines poses from coarse to fine by selectively retaining or discarding motion information from different layers based on gate estimations. Finally, temporal feature propagation is proposed to incorporate the historical motion information from point cloud sequences, and address the spatial inconsistency issue when transmitting motion information embedded in point clouds between frames. Experimental results on the KITTI odometry dataset and Argoverse dataset demonstrate that DSLO outperforms state-of-the-art methods, achieving at least a 15.67\% improvement on RTE and a 12.64\% improvement on RRE, while also achieving a 34.69\% reduction in runtime compared to baseline methods. Our implementation will be available at https://github.com/IRMVLab/DSLO.

Jiuming Liu, Guangming Wang, Zhe Liu et al.

Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale registration methods are rarely explored. Challenges mainly arise from the huge point number, complex distribution, and outliers of outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local features and then leverage estimators (eg. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose an end-to-end transformer network (RegFormer) for large-scale point cloud alignment without any further post-processing. Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers by extracting point features globally. Our transformer has linear complexity, which guarantees high efficiency even for large-scale scenes. Furthermore, to effectively reduce mismatches, a bijective association transformer is designed for regressing the initial transformation. Extensive experiments on KITTI and NuScenes datasets demonstrate that our RegFormer achieves competitive performance in terms of both accuracy and efficiency.

Guangming Wang, Xiaoyu Tian, Ruiqi Ding et al.

Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the ground truth of scene flow for training. Our method realizes the goal that training scene flow network with real-world data, which bridges the gap between training data and test data and broadens the scope of available data for training. Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions. Depth estimation and camera pose estimation obtain the depth maps and camera pose between two consecutive frames, which provide further information for the next scene flow estimation. After that, we used depth consistency loss, dynamic-static consistency loss, Chamfer loss, and Laplacian regularization loss to carry out unsupervised training of the scene flow network. To our knowledge, this is the first paper that realizes the unsupervised learning of 3D scene flow from monocular camera. The experiment results on KITTI show that our method for unsupervised learning of scene flow meets great performance compared to traditional methods Iterative Closest Point (ICP) and Fast Global Registration (FGR). The source code is available at: https://github.com/IRMVLab/3DUnMonoFlow.

Jiuming Liu, Guangming Wang, Weicai Ye et al.

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained searching ranges, and struggle with accumulated inaccuracy arising from the coarse-to-fine structure. To alleviate these problems, we propose a novel uncertainty-aware scene flow estimation network (DifFlow3D) with the diffusion probabilistic model. Iterative diffusion-based refinement is designed to enhance the correlation robustness and resilience to challenging cases, e.g. dynamics, noisy inputs, repetitive patterns, etc. To restrain the generation diversity, three key flow-related features are leveraged as conditions in our diffusion model. Furthermore, we also develop an uncertainty estimation module within diffusion to evaluate the reliability of estimated scene flow. Our DifFlow3D achieves state-of-the-art performance, with 24.0% and 29.1% EPE3D reduction respectively on FlyingThings3D and KITTI 2015 datasets. Notably, our method achieves an unprecedented millimeter-level accuracy (0.0078m in EPE3D) on the KITTI dataset. Additionally, our diffusion-based refinement paradigm can be readily integrated as a plug-and-play module into existing scene flow networks, significantly increasing their estimation accuracy. Codes are released at https://github.com/IRMVLab/DifFlow3D.

Yu Zheng, Guangming Wang, Jiuming Liu et al.

LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Recently, many works project the point cloud onto the 2D image and adopt the 2D Convolutional Neural Networks (CNNs) or vision transformer for LiDAR point cloud semantic segmentation. However, since more than one point can be projected onto the same 2D position but only one point can be preserved, the previous 2D image-based segmentation methods suffer from inevitable quantized information loss. To avoid quantized information loss, in this paper, we propose a novel spherical frustum structure. The points projected onto the same 2D position are preserved in the spherical frustums. Moreover, we propose a memory-efficient hash-based representation of spherical frustums. Through the hash-based representation, we propose the Spherical Frustum sparse Convolution (SFC) and Frustum Fast Point Sampling (F2PS) to convolve and sample the points stored in spherical frustums respectively. Finally, we present the Spherical Frustum sparse Convolution Network (SFCNet) to adopt 2D CNNs for LiDAR point cloud semantic segmentation without quantized information loss. Extensive experiments on the SemanticKITTI and nuScenes datasets demonstrate that our SFCNet outperforms the 2D image-based semantic segmentation methods based on conventional spherical projection. Codes will be available at https://github.com/IRMVLab/SFCNet.

Tianchen Deng, Wenhua Wu, Kunzhen Wu et al.

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates. However, the late motion average is often insufficient for effectively integrating spatial information, and its accuracy degrades in complex environments. In this paper, we present the first visual localization framework that performs multi-view spatial integration through an early-fusion mechanism, enabling robust operation in both structured and unstructured environments. Our framework is built upon the VGGT backbone, which encodes multi-view 3D geometry, and we introduce a pose tokenizer and projection module to more effectively exploit spatial relationships from multiple database views. Furthermore, we propose a novel sparse mask attention strategy that reduces computational cost by avoiding the quadratic complexity of global attention, thereby enabling real-time performance at scale. Trained on approximately eight million posed image pairs, Reloc-VGGT demonstrates strong accuracy and remarkable generalization ability. Extensive experiments across diverse public datasets consistently validate the effectiveness and efficiency of our approach, delivering high-quality camera pose estimates in real time while maintaining robustness to unseen environments. Our code and models will be publicly released upon acceptance.https://github.com/dtc111111/Reloc-VGGT.

Chaokang Jiang, Guangming Wang, Yanzi Miao et al.

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for estimating scene flow from images have limitations, which split the holistic nature of 3D scene flow by estimating optical flow and disparity separately. Learning 3D scene flow from point clouds also faces the difficulties of the gap between synthesized and real data and the sparsity of LiDAR point clouds. In this paper, the generated dense depth map is utilized to obtain explicit 3D coordinates, which achieves direct learning of 3D scene flow from 2D images. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Outliers in the generated 3D point cloud are removed by statistical methods to weaken the impact of noisy points on the 3D scene flow estimation task. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow. The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds. The comparisons of multiple scene flow metrics are shown to demonstrate the effectiveness and superiority of introducing pseudo-LiDAR point cloud to scene flow estimation.

Zi Wang, Mingkai Huang, Zhang Shi et al.

Multimodal cardiovascular magnetic resonance (CMR) imaging provides comprehensive and non-invasive insights into cardiovascular disease (CVD) diagnosis and underlying mechanisms. Despite decades of advancements, its widespread clinical adoption remains constrained by prolonged scan times and heterogeneity across medical environments. This underscores the urgent need for a generalist reconstruction foundation model for ultra-fast CMR imaging, one capable of adapting across diverse imaging scenarios and serving as the essential substrate for all downstream analyses. To enable this goal, we curate MMCMR-427K, the largest and most comprehensive multimodal CMR k-space database to date, comprising 427,465 multi-coil k-space data paired with structured metadata across 13 international centers, 12 CMR modalities, 15 scanners, and 17 CVD categories in populations across three continents. Building on this unprecedented resource, we introduce CardioMM, a generalist reconstruction foundation model capable of dynamically adapting to heterogeneous fast CMR imaging scenarios. CardioMM unifies semantic contextual understanding with physics-informed data consistency to deliver robust reconstructions across varied scanners, protocols, and patient presentations. Comprehensive evaluations demonstrate that CardioMM achieves state-of-the-art performance in the internal centers and exhibits strong zero-shot generalization to unseen external settings. Even at imaging acceleration up to 24x, CardioMM reliably preserves key cardiac phenotypes, quantitative myocardial biomarkers, and diagnostic image quality, enabling a substantial increase in CMR examination throughput without compromising clinical integrity. Together, our open-access MMCMR-427K database and CardioMM framework establish a scalable pathway toward high-throughput, high-quality, and clinically accessible cardiovascular imaging.

Huiying Deng, Guangming Wang, Zhiheng Feng et al.

In the existing methods, LiDAR odometry shows superior performance, but visual odometry is still widely used for its price advantage. Conventionally, the task of visual odometry mainly rely on the input of continuous images. However, it is very complicated for the odometry network to learn the epipolar geometry information provided by the images. In this paper, the concept of pseudo-LiDAR is introduced into the odometry to solve this problem. The pseudo-LiDAR point cloud back-projects the depth map generated by the image into the 3D point cloud, which changes the way of image representation. Compared with the stereo images, the pseudo-LiDAR point cloud generated by the stereo matching network can get the explicit 3D coordinates. Since the 6 Degrees of Freedom (DoF) pose transformation occurs in 3D space, the 3D structure information provided by the pseudo-LiDAR point cloud is more direct than the image. Compared with sparse LiDAR, the pseudo-LiDAR has a denser point cloud. In order to make full use of the rich point cloud information provided by the pseudo-LiDAR, a projection-aware dense odometry pipeline is adopted. Most previous LiDAR-based algorithms sampled 8192 points from the point cloud as input to the odometry network. The projection-aware dense odometry pipeline takes all the pseudo-LiDAR point clouds generated from the images except for the error points as the input to the network. While making full use of the 3D geometric information in the images, the semantic information in the images is also used in the odometry task. The fusion of 2D-3D is achieved in an image-only based odometry. Experiments on the KITTI dataset prove the effectiveness of our method. To the best of our knowledge, this is the first visual odometry method using pseudo-LiDAR.

Liang Song, Guangming Wang, Jiuming Liu et al.

In recent studies, the generalization of neural radiance fields for novel view synthesis task has been widely explored. However, existing methods are limited to objects and indoor scenes. In this work, we extend the generalization task to outdoor scenes, trained only on object-level datasets. This approach presents two challenges. Firstly, the significant distributional shift between training and testing scenes leads to black artifacts in rendering results. Secondly, viewpoint changes in outdoor scenes cause ghosting or missing regions in rendered images. To address these challenges, we propose a geometric correction module and an appearance correction module based on multi-head attention mechanisms. We normalize rendered depth and combine it with light direction as query in the attention mechanism. Our network effectively corrects varying scene structures and geometric features in outdoor scenes, generalizing well from object-level to unseen outdoor scenes. Additionally, we use appearance correction module to correct appearance features, preventing rendering artifacts like blank borders and ghosting due to viewpoint changes. By combining these modules, our approach successfully tackles the challenges of outdoor scene generalization, producing high-quality rendering results. When evaluated on four datasets (Blender, DTU, LLFF, Spaces), our network outperforms previous methods. Notably, compared to MVSNeRF, our network improves average PSNR from 19.369 to 25.989, SSIM from 0.838 to 0.889, and reduces LPIPS from 0.265 to 0.224 on Spaces outdoor scenes.

Chaokang Jiang, Guangming Wang, Jinxing Wu et al.

Promising complementarity exists between the texture features of color images and the geometric information of LiDAR point clouds. However, there still present many challenges for efficient and robust feature fusion in the field of 3D object detection. In this paper, first, unstructured 3D point clouds are filled in the 2D plane and 3D point cloud features are extracted faster using projection-aware convolution layers. Further, the corresponding indexes between different sensor signals are established in advance in the data preprocessing, which enables faster cross-modal feature fusion. To address LiDAR points and image pixels misalignment problems, two new plug-and-play fusion modules, LiCamFuse and BiLiCamFuse, are proposed. In LiCamFuse, soft query weights with perceiving the Euclidean distance of bimodal features are proposed. In BiLiCamFuse, the fusion module with dual attention is proposed to deeply correlate the geometric and textural features of the scene. The quantitative results on the KITTI dataset demonstrate that the proposed method achieves better feature-level fusion. In addition, the proposed network shows a shorter running time compared to existing methods.

Yueling Shen, Guangming Wang, Hesheng Wang

3D Multi-Object Tracking (MOT) is an important part of the unmanned vehicle perception module. Most methods optimize object detection and data association independently. These methods make the network structure complicated and limit the improvement of MOT accuracy. we proposed a 3D MOT framework based on simultaneous optimization of object detection and scene flow estimation. In the framework, a detection-guidance scene flow module is proposed to relieve the problem of incorrect inter-frame assocation. For more accurate scene flow label especially in the case of motion with rotation, a box-transformation-based scene flow ground truth calculation method is proposed. Experimental results on the KITTI MOT dataset show competitive results over the state-of-the-arts and the robustness under extreme motion with rotation.

Guangming Wang, Zhiheng Feng, Chaokang Jiang et al.

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point's movement. Scene flow estimation is used in various applications such as autonomous driving fields, activity recognition, and virtual reality fields. As it is challenging to annotate scene flow with ground truth for real-world data, this leaves no real-world dataset available to provide a large amount of data with ground truth for scene flow estimation. Therefore, many works use synthesized data to pre-train their network and real-world LiDAR data to finetune. Unlike the previous unsupervised learning of scene flow in point clouds, we propose to use odometry information to assist the unsupervised learning of scene flow and use real-world LiDAR data to train our network. Supervised odometry provides more accurate shared cost volume for scene flow. In addition, the proposed network has mask-weighted warp layers to get a more accurate predicted point cloud. The warp operation means applying an estimated pose transformation or scene flow to a source point cloud to obtain a predicted point cloud and is the key to refining scene flow from coarse to fine. When performing warp operations, the points in different states use different weights for the pose transformation and scene flow transformation. We classify the states of points as static, dynamic, and occluded, where the static masks are used to divide static and dynamic points, and the occlusion masks are used to divide occluded points. The mask-weighted warp layer indicates that static masks and occlusion masks are used as weights when performing warp operations. Our designs are proved to be effective in ablation experiments. The experiment results show the promising prospect of an odometry-assisted unsupervised learning method for 3D scene flow in real-world data.

Siting Zhu, Ziyun Lu, Guangming Wang et al.

Open-vocabulary scene understanding is crucial for robotic applications, enabling robots to comprehend complex 3D environmental contexts and supporting various downstream tasks such as navigation and manipulation. However, existing methods require pre-built complete 3D semantic maps to construct scene graphs for scene understanding, which limits their applicability in robotic scenarios where environments are explored incrementally. To address this challenge, we propose OGScene3D, an open-vocabulary scene understanding system that achieves accurate 3D semantic mapping and scene graph construction incrementally. Our system employs a confidence-based Gaussian semantic representation that jointly models semantic predictions and their reliability, enabling robust scene modeling. Building on this representation, we introduce a hierarchical 3D semantic optimization strategy that achieves semantic consistency through local correspondence establishment and global refinement, thereby constructing globally consistent semantic maps. Moreover, we design a long-term global optimization method that leverages temporal memory of historical observations to enhance semantic predictions. By integrating 2D-3D semantic consistency with Gaussian rendering contribution, this method continuously refines the semantic understanding of the entire scene. Furthermore, we develop a progressive graph construction approach that dynamically creates and updates both nodes and semantic relationships, allowing continuous updating of the 3D scene graphs. Extensive experiments on widely used datasets and real-world scenes demonstrate the effectiveness of our OGScene3D on open-vocabulary scene understanding.

Jiuming Liu, Guangming Wang, Zhe Liu et al.

Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challenges mainly arise from the huge point scale, complex point distribution, and numerous outliers within outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local descriptors and then leverage robust estimators (e.g. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose a novel end-to-end differential transformer network, termed RegFormer++, for large-scale point cloud alignment without requiring any further post-processing. Specifically, a hierarchical projection-aware 2D transformer with linear complexity is proposed to project raw LiDAR points onto a cylindrical surface and extract global point features, which can improve resilience to outliers due to long-range dependencies. Because we fill original 3D coordinates into 2D projected positions, our designed transformer can benefit from both high efficiency in 2D processing and accuracy from 3D geometric information. Furthermore, to effectively reduce wrong point matching, a Bijective Association Transformer (BAT) is designed, combining both cross attention and all-to-all point gathering. To improve training stability and robustness, a feature-transformed optimal transport module is also designed for regressing the final pose transformation. Extensive experiments on KITTI, NuScenes, and Argoverse datasets demonstrate that our model achieves state-of-the-art performance in terms of both accuracy and efficiency.

Junyi Ma, Erhang Zhang, Haoran Yang et al.

A critical bottleneck hindering further advancement in embodied AI and robotics is the challenge of scaling robot data. To address this, the field of learning robot manipulation skills from human video data has attracted rapidly growing attention in recent years, driven by the abundance of human activity videos and advances in computer vision. This line of research promises to enable robots to acquire skills passively from the vast and readily available resource of human demonstrations, substantially favoring scalable learning for generalist robotic systems. Therefore, we present this survey to provide a comprehensive and up-to-date review of human-video-based learning techniques in robotics, focusing on both human-robot skill transfer and data foundations. We first review the policy learning foundations in robotics, and then describe the fundamental interfaces to incorporate human videos. Subsequently, we introduce a hierarchical taxonomy of transferring human videos to robot skills, covering task-, observation-, and action-oriented pathways, along with a cross-family analysis of their couplings with different data configurations and learning paradigms. In addition, we investigate the data foundations including widely-used human video datasets and video generation schemes, and provide large-scale statistical trends in dataset development and utilization. Ultimately, we emphasize the challenges and limitations intrinsic to this field, and delineate potential avenues for future research. The paper list of our survey is available at https://github.com/IRMVLab/awesome-robot-learning-from-human-videos.

Hao Shi, Song Wang, Jiaming Zhang et al.

Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard processing, struggle with simultaneous geometric and semantic estimation, continuity across varying viewpoints, and single-view occlusion. Our paper introduces OccFiner, a novel offboard framework designed to enhance the accuracy of vision-based occupancy predictions. OccFiner operates in two hybrid phases: 1) a multi-to-multi local propagation network that implicitly aligns and processes multiple local frames for correcting onboard model errors and consistently enhancing occupancy accuracy across all distances. 2) the region-centric global propagation, focuses on refining labels using explicit multi-view geometry and integrating sensor bias, particularly for increasing the accuracy of distant occupied voxels. Extensive experiments demonstrate that OccFiner improves both geometric and semantic accuracy across various types of coarse occupancy, setting a new state-of-the-art performance on the SemanticKITTI dataset. Notably, OccFiner significantly boosts the performance of vision-based SSC models, achieving accuracy levels competitive with established LiDAR-based onboard SSC methods. Furthermore, OccFiner is the first to achieve automatic annotation of SSC in a purely vision-based approach. Quantitative experiments prove that OccFiner successfully facilitates occupancy data loop-closure in autonomous driving. Additionally, we quantitatively and qualitatively validate the superiority of the offboard approach on city-level SSC static maps. The source code will be made publicly available at https://github.com/MasterHow/OccFiner.

Chang Nie, Tianchen Deng, Guangming Wang et al.

While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts or focus exclusively on human speech. This leaves a significant gap in real-time, sound-centric manipulation where fleeting environmental acoustics provide critical state verification during task execution. Consequently, key sounds are easily missed due to low-frequency updates or system latency. This problem is exacerbated by action chunking with open-loop execution, which creates a Blind Execution Interval where acoustic events are lost between discrete audio observation windows. Recognizing the necessity of continuous auditory awareness, we formalize Vision-Sound-Language-Action (VSLA) as a continuous control paradigm conditioned on vision, streaming audio, language, and proprioception under delayed decision loops. As an instantiation, we introduce HEAR, a VSLA framework integrating four components: (i) a streaming Historizer to maintain a compact, causal audio context across execution gaps; (ii) an Envisioner adapted from omni foundation models to reason over multi-sensory inputs; (iii) an Advancer, formulated as an audio world model, to learn temporal dynamics by predicting near-future audio codes; and (iv) a flow-matching Realizer policy to generate smooth action chunks. To address the scarcity of pretraining data and evaluations for VSLA, we construct OpenX-Sound for pretraining, alongside HEAR-Bench, the first sound-centric manipulation benchmark with strict causal timing rules. Our results suggest that robust sound-centric manipulation necessitates causal persistence and explicit temporal learning. This framework provides a practical step toward multi-sensory foundation models for embodied agents, enabling robots to perceive and interact with dynamic environments. Code and videos are available at https://hear.irmv.top.

Sixu Lin, Junliang Chen, Huaiyuan Xu et al.

Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predictive flow planners to guide 3D manipulation, existing approaches often rely on modular pipelines stacking multiple submodels, resulting in high computational overhead and limited real-time performance. To address these challenges, we introduce RoboFlow4D, a lightweight flow world model that unifies perception and planning by estimating temporal motion in physical 3D space. As an end-to-end framework, RoboFlow4D directly predicts multi-frame 3D flows from visual observations and textual instructions, providing explicit flow-based planning to guide action generation. This design allows seamless integration with general action policies, forming an efficient observation-planning-execution closed loop. Through slow-fast collaboration between flow prediction and action control, RoboFlow4D enables real-time and resource-efficient manipulation. Extensive experiments in both simulation and real-world settings demonstrate that RoboFlow4D consistently improves manipulation success rates and computational efficiency, advancing flow-guided planning for embodied intelligence.

Tinghuai Wang, Guangming Wang, Kuan Eeik Tan

Convolutional neural networks (CNN) have made significant advances in detecting roads from satellite images. However, existing CNN approaches are generally repurposed semantic segmentation architectures and suffer from the poor delineation of long and curved regions. Lack of overall road topology and structure information further deteriorates their performance on challenging remote sensing images. This paper presents a novel multi-task graph neural network (GNN) which simultaneously detects both road regions and road borders; the inter-play between these two tasks unlocks superior performance from two perspectives: (1) the hierarchically detected road borders enable the network to capture and encode holistic road structure to enhance road connectivity (2) identifying the intrinsic correlation of semantic landcover regions mitigates the difficulty in recognizing roads cluttered by regions with similar appearance. Experiments on challenging dataset demonstrate that the proposed architecture can improve the road border delineation and road extraction accuracy compared with the existing methods.

Chang Nie, Yiqing Xu, Guangming Wang et al.

Moving object segmentation plays a vital role in understanding dynamic visual environments. While existing methods rely on multi-frame image sequences to identify moving objects, single-image MOS is critical for applications like motion intention prediction and handling camera frame drops. However, segmenting moving objects from a single image remains challenging for existing methods due to the absence of temporal cues. To address this gap, we propose MovSAM, the first framework for single-image moving object segmentation. MovSAM leverages a Multimodal Large Language Model (MLLM) enhanced with Chain-of-Thought (CoT) prompting to search the moving object and generate text prompts based on deep thinking for segmentation. These prompts are cross-fused with visual features from the Segment Anything Model (SAM) and a Vision-Language Model (VLM), enabling logic-driven moving object segmentation. The segmentation results then undergo a deep thinking refinement loop, allowing MovSAM to iteratively improve its understanding of the scene context and inter-object relationships with logical reasoning. This innovative approach enables MovSAM to segment moving objects in single images by considering scene understanding. We implement MovSAM in the real world to validate its practical application and effectiveness for autonomous driving scenarios where the multi-frame methods fail. Furthermore, despite the inherent advantage of multi-frame methods in utilizing temporal information, MovSAM achieves state-of-the-art performance across public MOS benchmarks, reaching 92.5\% on J\&F. Our implementation will be available at https://github.com/IRMVLab/MovSAM.

Zian Wang, Lizhen Lan, Guangming Wang et al.

Imaging-derived phenotypes (IDPs) summarize multi-organ physiology but provide only static snapshots of diseases that evolve over time. In contrast, longitudinal electronic health records encode disease trajectories through temporal dependencies among past diagnosis events and comorbidity structure. We hypothesize that IDPs and disease trajectories contain partially shared disease-relevant structure. We propose a trajectory-aware distillation framework that transfers structural knowledge from a generative disease trajectory Transformer into an organ-wise IDP encoder. A population-scale trajectory model trained on longitudinal diagnosis sequences produces subject-level embeddings that supervise IDP representation learning via geometry-preserving alignment. During downstream prediction, trajectory and imaging representations can also be fused via cross-attention. Across 159 diseases in the UK Biobank cohort, trajectory-aware pretraining consistently improves both discrimination (AUC) and time-to-onset prediction (MAE), with the largest gains for low-prevalence diseases. Similarity relationships in IDP embedding space also align with those in trajectory space, providing supportive evidence for partially aligned representation geometry. These results suggest that population-scale generative disease models can serve as structural priors for data-limited imaging modalities, improving robustness under realistic cohort constraints.

Yixiong Jing, Cheng Zhang, Haibing Wu et al.

Point clouds are widely used for infrastructure monitoring by providing geometric information, where segmentation is required for downstream tasks such as defect detection. Existing research has automated semantic segmentation of structural components, while brick-level segmentation (identifying defects such as spalling and mortar loss) has been primarily conducted from RGB images. However, acquiring high-resolution images is impractical in low-light environments like masonry tunnels. Point clouds, though robust to dim lighting, are typically unstructured, sparse, and noisy, limiting fine-grained segmentation. We present InfraDiffusion, a zero-shot framework that projects masonry point clouds into depth maps using virtual cameras and restores them by adapting the Denoising Diffusion Null-space Model (DDNM). Without task-specific training, InfraDiffusion enhances visual clarity and geometric consistency of depth maps. Experiments on masonry bridge and tunnel point cloud datasets show significant improvements in brick-level segmentation using the Segment Anything Model (SAM), underscoring its potential for automated inspection of masonry assets. Our code and data is available at https://github.com/Jingyixiong/InfraDiffusion-official-implement.

Guangming Wang, Xinrui Wu, Shuyang Jiang et al.

An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper. In this architecture, the projection-aware representation of the 3D point cloud is proposed to organize the raw 3D point cloud into an ordered data form to achieve efficiency. The Pyramid, Warping, and Cost volume (PWC) structure for the LiDAR odometry task is built to estimate and refine the pose in a coarse-to-fine approach. A projection-aware attentive cost volume is built to directly associate two discrete point clouds and obtain embedding motion patterns. Then, a trainable embedding mask is proposed to weigh the local motion patterns to regress the overall pose and filter outlier points. The trainable pose warp-refinement module is iteratively used with embedding mask optimized hierarchically to make the pose estimation more robust for outliers. The entire architecture is holistically optimized end-to-end to achieve adaptive learning of cost volume and mask, and all operations involving point cloud sampling and grouping are accelerated by projection-aware 3D feature learning methods. The superior performance and effectiveness of our LiDAR odometry architecture are demonstrated on KITTI, M2DGR, and Argoverse datasets. Our method outperforms all recent learning-based methods and even the geometry-based approach, LOAM with mapping optimization, on most sequences of KITTI odometry dataset. We open sourced our codes at: https://github.com/IRMVLab/EfficientLO-Net.

Guangming Wang, Xinrui Wu, Zhe Liu et al.

A novel 3D point cloud learning model for deep LiDAR odometry, named PWCLO-Net, using hierarchical embedding mask optimization is proposed in this paper. In this model, the Pyramid, Warping, and Cost volume (PWC) structure for the LiDAR odometry task is built to refine the estimated pose in a coarse-to-fine approach hierarchically. An attentive cost volume is built to associate two point clouds and obtain embedding motion patterns. Then, a novel trainable embedding mask is proposed to weigh the local motion patterns of all points to regress the overall pose and filter outlier points. The estimated current pose is used to warp the first point cloud to bridge the distance to the second point cloud, and then the cost volume of the residual motion is built. At the same time, the embedding mask is optimized hierarchically from coarse to fine to obtain more accurate filtering information for pose refinement. The trainable pose warp-refinement process is iteratively used to make the pose estimation more robust for outliers. The superior performance and effectiveness of our LiDAR odometry model are demonstrated on KITTI odometry dataset. Our method outperforms all recent learning-based methods and outperforms the geometry-based approach, LOAM with mapping optimization, on most sequences of KITTI odometry dataset.Our source codes will be released on https://github.com/IRMVLab/PWCLONet.

Guangming Wang, Chi Zhang, Hesheng Wang et al.

In autonomous driving, monocular sequences contain lots of information. Monocular depth estimation, camera ego-motion estimation and optical flow estimation in consecutive frames are high-profile concerns recently. By analyzing tasks above, pixels in the middle frame are modeled into three parts: the rigid region, the non-rigid region, and the occluded region. In joint unsupervised training of depth and pose, we can segment the occluded region explicitly. The occlusion information is used in unsupervised learning of depth, pose and optical flow, as the image reconstructed by depth-pose and optical flow will be invalid in occluded regions. A less-than-mean mask is designed to further exclude the mismatched pixels interfered with by motion or illumination change in the training of depth and pose networks. This method is also used to exclude some trivial mismatched pixels in the training of the optical flow network. Maximum normalization is proposed for depth smoothness term to restrain depth degradation in textureless regions. In the occluded region, as depth and camera motion can provide more reliable motion estimation, they can be used to instruct unsupervised learning of optical flow. Our experiments in KITTI dataset demonstrate that the model based on three regions, full and explicit segmentation of the occlusion region, the rigid region, and the non-rigid region with corresponding unsupervised losses can improve performance on three tasks significantly. The source code is available at: https://github.com/guangmingw/DOPlearning.

Yixiong Jing, Xingyuan Chen, Guangming Wang et al.

Physics-based digital twins aim to predict the dynamics of real-world objects under interaction, enabling real-to-sim-to-real applications in robotics. Current approaches reconstruct such twins as explicit physical models (such as spring-mass systems) to predict the dynamics, but the resulting models often inherit the resolution of the visual reconstruction rather than being reduced to the physical complexity required to reproduce task-relevant dynamics. This mismatch introduces redundant topology, making repeated forward-dynamics rollouts unnecessarily expensive. To address this challenge, we present PhySPRING, an fully differentiable GNN-based method to reduce complexity in spring--mass digital twins. PhySPRING jointly learns a hierarchy of coarsened graph topologies and their mechanical parameters from observations. At each reduction level, PhySPRING merges nodes with similar learned dynamic responses to optimize the topology, while maintaining every reduced layer as an explicit spring--mass system. On the PhysTwin benchmark, PhySPRING improves dense reconstruction and prediction accuracy over PhysTwin, while reduced models retain stable physical and visual fidelity with up to a 2.30 times speed-up. We further demonstrate the effectiveness of PhySPRING in a Real2Sim robot policy-evaluation pipeline, where the reduced models are substituted zero-shot into ACT and $π_0$ evaluations, maintaining comparable manipulation success rates across downsampling levels while improving action-sampling effectiveness. Together, PhySPRING enables efficient and structure-preserving spring--mass reduction without sacrificing fidelity or robotic utility.

Siting Zhu, Renjie Qin, Guangming Wang et al.

We propose SemGauss-SLAM, a dense semantic SLAM system utilizing 3D Gaussian representation, that enables accurate 3D semantic mapping, robust camera tracking, and high-quality rendering simultaneously. In this system, we incorporate semantic feature embedding into 3D Gaussian representation, which effectively encodes semantic information within the spatial layout of the environment for precise semantic scene representation. Furthermore, we propose feature-level loss for updating 3D Gaussian representation, enabling higher-level guidance for 3D Gaussian optimization. In addition, to reduce cumulative drift in tracking and improve semantic reconstruction accuracy, we introduce semantic-informed bundle adjustment. By leveraging multi-frame semantic associations, this strategy enables joint optimization of 3D Gaussian representation and camera poses, resulting in low-drift tracking and accurate semantic mapping. Our SemGauss-SLAM demonstrates superior performance over existing radiance field-based SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in high-precision semantic segmentation and dense semantic mapping.

Chaokang Jiang, Guangming Wang, Jiuming Liu et al.

Learning 3D scene flow from LiDAR point clouds presents significant difficulties, including poor generalization from synthetic datasets to real scenes, scarcity of real-world 3D labels, and poor performance on real sparse LiDAR point clouds. We present a novel approach from the perspective of auto-labelling, aiming to generate a large number of 3D scene flow pseudo labels for real-world LiDAR point clouds. Specifically, we employ the assumption of rigid body motion to simulate potential object-level rigid movements in autonomous driving scenarios. By updating different motion attributes for multiple anchor boxes, the rigid motion decomposition is obtained for the whole scene. Furthermore, we developed a novel 3D scene flow data augmentation method for global and local motion. By perfectly synthesizing target point clouds based on augmented motion parameters, we easily obtain lots of 3D scene flow labels in point clouds highly consistent with real scenarios. On multiple real-world datasets including LiDAR KITTI, nuScenes, and Argoverse, our method outperforms all previous supervised and unsupervised methods without requiring manual labelling. Impressively, our method achieves a tenfold reduction in EPE3D metric on the LiDAR KITTI dataset, reducing it from $0.190m$ to a mere $0.008m$ error.

Wenhua Wu, Qi Wang, Guangming Wang et al.

Road surface reconstruction plays a vital role in autonomous driving systems, enabling road lane perception and high-precision mapping. Recently, neural implicit encoding has achieved remarkable results in scene representation, particularly in the realistic rendering of scene textures. However, it faces challenges in directly representing geometric information for large-scale scenes. To address this, we propose EMIE-MAP, a novel method for large-scale road surface reconstruction based on explicit mesh and implicit encoding. The road geometry is represented using explicit mesh, where each vertex stores implicit encoding representing the color and semantic information. To overcome the difficulty in optimizing road elevation, we introduce a trajectory-based elevation initialization and an elevation residual learning method based on Multi-Layer Perceptron (MLP). Additionally, by employing implicit encoding and multi-camera color MLPs decoding, we achieve separate modeling of scene physical properties and camera characteristics, allowing surround-view reconstruction compatible with different camera models. Our method achieves remarkable road surface reconstruction performance in a variety of real-world challenging scenarios.

Guangming Wang, Lei Pan, Songyou Peng et al.

Detailed and realistic 3D environment representations have been a long-standing goal in the fields of computer vision and robotics. The recent emergence of neural implicit representations has introduced significant advances to these domains, enabling numerous novel capabilities. Among these, Neural Radiance Fields (NeRFs) have gained considerable attention because of their considerable representational advantages, such as simplified mathematical models, low memory footprint, and continuous scene representations. In addition to computer vision, NeRFs have demonstrated significant potential in robotics. Thus, we present this survey to provide a comprehensive understanding of NeRFs in the field of robotics. By exploring the advantages and limitations of NeRF as well as its current applications and future potential, we aim to provide an overview of this promising area of research. Our survey is divided into two main sections: \textit{Applications of NeRFs in Robotics} and \textit{Advances for NeRFs in Robotics}, from the perspective of how NeRF enters the field of robotics. In the first section, we introduce and analyze some works that have been or could be used in robotics for perception and interaction tasks. In the second section, we show some works related to improving NeRF's own properties, which are essential for deploying NeRFs in robotics. In the discussion section of the review, we summarize the existing challenges and provide valuable future research directions.

Wenhua Wu, Guangming Wang, Ting Deng et al.

Recent research on Simultaneous Localization and Mapping (SLAM) based on implicit representation has shown promising results in indoor environments. However, there are still some challenges: the limited scene representation capability of implicit encodings, the uncertainty in the rendering process from implicit representations, and the disruption of consistency by dynamic objects. To address these challenges, we propose a real-time dynamic visual SLAM system based on local-global fusion neural implicit representation, named DVN-SLAM. To improve the scene representation capability, we introduce a local-global fusion neural implicit representation that enables the construction of an implicit map while considering both global structure and local details. To tackle uncertainties arising from the rendering process, we design an information concentration loss for optimization, aiming to concentrate scene information on object surfaces. The proposed DVN-SLAM achieves competitive performance in localization and mapping across multiple datasets. More importantly, DVN-SLAM demonstrates robustness in dynamic scenes, a trait that sets it apart from other NeRF-based methods.

Jiaqi Li, Guangming Wang, Shuntian Zheng et al.

Temporal Action Localization (TAL) requires identifying both the boundaries and categories of actions in untrimmed videos. While vision-language models (VLMs) offer rich semantics to complement visual evidence, existing approaches tend to overemphasize linguistic priors at the expense of visual performance, leading to a pronounced modality bias. We propose ActionVLM, a vision-language aggregation framework that systematically mitigates modality bias in TAL. Our key insight is to preserve vision as the dominant signal while adaptively exploiting language only when beneficial. To this end, we introduce (i) a debiasing reweighting module that estimates the language advantage-the incremental benefit of language over vision-only predictions-and dynamically reweights language modality accordingly, and (ii) a residual aggregation strategy that treats language as a complementary refinement rather than the primary driver. This combination alleviates modality bias, reduces overconfidence from linguistic priors, and strengthens temporal reasoning. Experiments on THUMOS14 show that our model outperforms state-of-the-art by up to 3.2% mAP.

Yuxuan Wu, Guangming Wang, Zhiheng Yang et al.

Developing general robot intelligence in open environments requires continual skill learning. Recent Vision-Language-Action (VLA) models leverage massive pretraining data to support diverse manipulation tasks, but they still depend heavily on task-specific fine-tuning, revealing a lack of continual learning capability. Existing continual learning methods are also resource-intensive to scale to VLA models. We propose Stellar VLA, a knowledge-driven continual learning framework with two variants: T-Stellar, modeling task-centric knowledge space, and TS-Stellar, capturing hierarchical task-skill structure. Stellar VLA enables self-supervised knowledge evolution through joint learning of task latent representation and the knowledge space, reducing annotation needs. Knowledge-guided expert routing provide task specialization without extra network parameters, lowering training overhead. Experiments on the LIBERO benchmark and real-world tasks show over 50 percentage average improvement in final success rates relative to baselines. TS-Stellar further excels in complex action inference, and in-depth analyses verify effective knowledge retention and discovery. Our code will be released soon.

Chang Nie, Guangming Wang, Zhe Lie et al.

Robot imitation learning relies on 4D multi-view sequential images. However, the high cost of data collection and the scarcity of high-quality data severely constrain the generalization and application of embodied intelligence policies like Vision-Language-Action (VLA) models. Data augmentation is a powerful strategy to overcome data scarcity, but methods for editing 4D multi-view sequential images for manipulation tasks are currently lacking. Thus, we propose ERMV (Editing Robotic Multi-View 4D data), a novel data augmentation framework that efficiently edits an entire multi-view sequence based on single-frame editing and robot state conditions. This task presents three core challenges: (1) maintaining geometric and appearance consistency across dynamic views and long time horizons; (2) expanding the working window with low computational costs; and (3) ensuring the semantic integrity of critical objects like the robot arm. ERMV addresses these challenges through a series of innovations. First, to ensure spatio-temporal consistency in motion blur, we introduce a novel Epipolar Motion-Aware Attention (EMA-Attn) mechanism that learns pixel shift caused by movement before applying geometric constraints. Second, to maximize the editing working window, ERMV pioneers a Sparse Spatio-Temporal (STT) module, which decouples the temporal and spatial views and remodels a single-frame multi-view problem through sparse sampling of the views to reduce computational demands. Third, to alleviate error accumulation, we incorporate a feedback intervention Mechanism, which uses a Multimodal Large Language Model (MLLM) to check editing inconsistencies and request targeted expert guidance only when necessary. Extensive experiments demonstrate that ERMV-augmented data significantly boosts the robustness and generalization of VLA models in both simulated and real-world environments.

Guangming Wang, Chensheng Peng, Jinpeng Zhang et al.

Multiple object tracking (MOT) is a significant task in achieving autonomous driving. Traditional works attempt to complete this task, either based on point clouds (PC) collected by LiDAR, or based on images captured from cameras. However, relying on one single sensor is not robust enough, because it might fail during the tracking process. On the other hand, feature fusion from multiple modalities contributes to the improvement of accuracy. As a result, new techniques based on different sensors integrating features from multiple modalities are being developed. Texture information from RGB cameras and 3D structure information from Lidar have respective advantages under different circumstances. However, it's not easy to achieve effective feature fusion because of completely distinct information modalities. Previous fusion methods usually fuse the top-level features after the backbones extract the features from different modalities. In this paper, we first introduce PointNet++ to obtain multi-scale deep representations of point cloud to make it adaptive to our proposed Interactive Feature Fusion between multi-scale features of images and point clouds. Specifically, through multi-scale interactive query and fusion between pixel-level and point-level features, our method, can obtain more distinguishing features to improve the performance of multiple object tracking. Besides, we explore the effectiveness of pre-training on each single modality and fine-tuning on the fusion-based model. The experimental results demonstrate that our method can achieve good performance on the KITTI benchmark and outperform other approaches without using multi-scale feature fusion. Moreover, the ablation studies indicates the effectiveness of multi-scale feature fusion and pre-training on single modality.

Guangming Wang, Jiquan Zhong, Shijie Zhao et al.

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization.

Guangming Wang, Yunzhe Hu, Xinrui Wu et al.

Scene flow estimation is the task to predict the point-wise or pixel-wise 3D displacement vector between two consecutive frames of point clouds or images, which has important application in fields such as service robots and autonomous driving. Although many previous works have explored greatly on scene flow estimation based on point clouds, there are two problems that have not been noticed or well solved before: 1) Points of adjacent frames in repetitive patterns may be wrongly associated due to similar spatial structure in their neighbourhoods; 2) Scene flow between adjacent frames of point clouds with long-distance movement may be inaccurately estimated. To solve the first problem, a novel context-aware set convolution layer is proposed in this paper to exploit contextual structure information of Euclidean space and learn soft aggregation weights for local point features. This design is inspired by human perception of contextual structure information during scene understanding with repetitive patterns. The context-aware set convolution layer is incorporated in a context-aware point feature pyramid module of 3D point clouds for scene flow estimation. For the second problem, an explicit residual flow learning structure is proposed in the residual flow refinement layer to cope with long-distance movement. The experiments and ablation study on FlyingThings3D and KITTI scene flow datasets demonstrate the effectiveness of each proposed component. The qualitative results show that the problems of ambiguous inter-frame association and long-distance movement estimation are well handled. Quantitative results on both FlyingThings3D and KITTI scene flow datasets show that the proposed method achieves state-of-the-art performance, surpassing all other previous works to the best of our knowledge by at least 25%.

Guangming Wang, Shuaiqi Ren, Hesheng Wang

Optical flow estimation is a fundamental problem of computer vision and has many applications in the fields of robot learning and autonomous driving. This paper reveals novel geometric laws of optical flow based on the insight and detailed definition of non-occlusion. Then, two novel loss functions are proposed for the unsupervised learning of optical flow based on the geometric laws of non-occlusion. Specifically, after the occlusion part of the images are masked, the flowing process of pixels is carefully considered and geometric constraints are conducted based on the geometric laws of optical flow. First, neighboring pixels in the first frame will not intersect during the pixel displacement to the second frame. Secondly, when the cluster containing adjacent four pixels in the first frame moves to the second frame, no other pixels will flow into the quadrilateral formed by them. According to the two geometrical constraints, the optical flow non-intersection loss and the optical flow non-blocking loss in the non-occlusion regions are proposed. Two loss functions punish the irregular and inexact optical flows in the non-occlusion regions. The experiments on datasets demonstrated that the proposed unsupervised losses of optical flow based on the geometric laws in non-occlusion regions make the estimated optical flow more refined in detail, and improve the performance of unsupervised learning of optical flow. In addition, the experiments training on synthetic data and evaluating on real data show that the generalization ability of optical flow network is improved by our proposed unsupervised approach.

Guangming Wang, Honghao Zeng, Ziliang Wang et al.

Real-time 3D human pose estimation is crucial for human-computer interaction. It is cheap and practical to estimate 3D human pose only from monocular video. However, recent bone splicing based 3D human pose estimation method brings about the problem of cumulative error. In this paper, the concept of virtual bones is proposed to solve such a challenge. The virtual bones are imaginary bones between non-adjacent joints. They do not exist in reality, but they bring new loop constraints for the estimation of 3D human joints. The proposed network in this paper predicts real bones and virtual bones, simultaneously. The final length of real bones is constrained and learned by the loop constructed by the predicted real bones and virtual bones. Besides, the motion constraints of joints in consecutive frames are considered. The consistency between the 2D projected position displacement predicted by the network and the captured real 2D displacement by the camera is proposed as a new projection consistency loss for the learning of 3D human pose. The experiments on the Human3.6M dataset demonstrate the good performance of the proposed method. Ablation studies demonstrate the effectiveness of the proposed inter-frame projection consistency constraints and intra-frame loop constraints.

Guangming Wang, Hesheng Wang, Yiling Liu et al.

A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper. The depth estimation network and the ego-motion estimation network are trained according to the constraints of depth and ego-motion without truth values. The main contribution of our method is to carefully consider the occlusion of the pixels generated when the adjacent frames are projected to each other, and the blank problem generated in the projection target imaging plane. Two fine masks are designed to solve most of the image pixel mismatch caused by the movement of the camera. In addition, some relatively rare circumstances are considered, and repeated masking is proposed. To some extent, the method is to use a geometric relationship to filter the mismatched pixels for training, making unsupervised learning more efficient and accurate. The experiments on KITTI dataset show our method achieves good performance in terms of depth and ego-motion. The generalization capability of our method is demonstrated by training on the low-quality uncalibrated bike video dataset and evaluating on KITTI dataset, and the results are still good.

Guangming Wang, Muyao Chen, Hanwen Liu et al.

With the rapid development of measurement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets.

Guangming Wang, Yehui Yang, Huixin Zhang et al.

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset.

Guangming Wang, Minjian Xin, Wenhua Wu et al.

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporates the existing base controllers into stages of exploration, value learning, and policy update. Furthermore, we present a straightforward way of synthesizing different base controllers to integrate their strengths. Through experiments ranging from stacking blocks to cups, it is demonstrated that the learned state-based or image-based policies steadily outperform base controllers. Compared to previous works of learning from demonstrations, our method improves sample efficiency by orders of magnitude and improves the performance. Overall, our method bears the potential of leveraging existing industrial robot manipulation systems to build more flexible and intelligent controllers.

Guangming Wang, Xinrui Wu, Zhe Liu et al.

Scene flow represents the 3D motion of every point in the dynamic environments. Like the optical flow that represents the motion of pixels in 2D images, 3D motion representation of scene flow benefits many applications, such as autonomous driving and service robot. This paper studies the problem of scene flow estimation from two consecutive 3D point clouds. In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer. The proposed network has a new more-for-less hierarchical architecture. The more-for-less means that the number of input points is greater than the number of output points for scene flow estimation, which brings more input information and balances the precision and resource consumption. In this hierarchical architecture, scene flow of different levels is generated and supervised respectively. A novel attentive embedding module is introduced to aggregate the features of adjacent points using a double attention method in a patch-to-patch manner. The proper layers for flow embedding and flow supervision are carefully considered in our network designment. Experiments show that the proposed network outperforms the state-of-the-art performance of 3D scene flow estimation on the FlyingThings3D and KITTI Scene Flow 2015 datasets. We also apply the proposed network to realistic LiDAR odometry task, which is an key problem in autonomous driving. The experiment results demonstrate that our proposed network can outperform the ICP-based method and shows the good practical application ability.

Tinghuai Wang, Guangming Wang, Kuan Eeik Tan et al.

Convolutional neural networks (CNN) have made significant advances in hyperspectral image (HSI) classification. However, standard convolutional kernel neglects the intrinsic connections between data points, resulting in poor region delineation and small spurious predictions. Furthermore, HSIs have a unique continuous data distribution along the high dimensional spectrum domain - much remains to be addressed in characterizing the spectral contexts considering the prohibitively high dimensionality and improving reasoning capability in light of the limited amount of labelled data. This paper presents a novel architecture which explicitly addresses these two issues. Specifically, we design an architecture to encode the multiple spectral contextual information in the form of spectral pyramid of multiple embedding spaces. In each spectral embedding space, we propose graph attention mechanism to explicitly perform interpretable reasoning in the spatial domain based on the connection in spectral feature space. Experiments on three HSI datasets demonstrate that the proposed architecture can significantly improve the classification accuracy compared with the existing methods.