Xingxing Zuo

Zuxing Lu, Ziang Zheng, Yao Lyu et al.

Building a general-purpose whole-body controller is essential for enabling diverse motion capabilities in humanoid robots across a wide range of downstream tasks, including locomotion and loco-manipulation. Different tasks rely on distinct motion reference modalities: locomotion primarily depends on coordinated robot joint trajectories, whereas manipulation requires precise end-effector trajectory tracking. Existing methods often overlook the representational mismatch between dense robot joint angles and sparse end-effector poses. To address this, we propose Multi-Modal Mimic (M3imic), a versatile multi-modal whole-body control framework that unifies heterogeneous motion reference modalities, including robot joint angles, human pose trajectories, and end-effector poses, using modality-specific encoders to map them into a shared latent space. Leveraging large-scale reinforcement learning in the simulator, we train a single policy that achieves sim-to-real transfer across multiple motion reference modalities without modality-specific retraining. Extensive simulation and real-world experiments on the Unitree G1 robot are conducted to evaluate the proposed framework. In simulation, the policy achieves a peak success rate of 98.42\% on an unseen test dataset, demonstrating its exceptional generalization capability. The code is available at https://github.com/Renforce-Dynamics/MultiModalWBC

Ruida Zhang, Ziqin Huang, Gu Wang et al. · tsinghua

While RGBD-based methods for category-level object pose estimation hold promise, their reliance on depth data limits their applicability in diverse scenarios. In response, recent efforts have turned to RGB-based methods; however, they face significant challenges stemming from the absence of depth information. On one hand, the lack of depth exacerbates the difficulty in handling intra-class shape variation, resulting in increased uncertainty in shape predictions. On the other hand, RGB-only inputs introduce inherent scale ambiguity, rendering the estimation of object size and translation an ill-posed problem. To tackle these challenges, we propose LaPose, a novel framework that models the object shape as the Laplacian mixture model for Pose estimation. By representing each point as a probabilistic distribution, we explicitly quantify the shape uncertainty. LaPose leverages both a generalized 3D information stream and a specialized feature stream to independently predict the Laplacian distribution for each point, capturing different aspects of object geometry. These two distributions are then integrated as a Laplacian mixture model to establish the 2D-3D correspondences, which are utilized to solve the pose via the PnP module. In order to mitigate scale ambiguity, we introduce a scale-agnostic representation for object size and translation, enhancing training efficiency and overall robustness. Extensive experiments on the NOCS datasets validate the effectiveness of LaPose, yielding state-of-the-art performance in RGB-based category-level object pose estimation. Codes are released at https://github.com/lolrudy/LaPose

Lu Sang, Bjoern Haefner, Xingxing Zuo et al.

Fine-detailed reconstructions are in high demand in many applications. However, most of the existing RGB-D reconstruction methods rely on pre-calculated accurate camera poses to recover the detailed surface geometry, where the representation of a surface needs to be adapted when optimizing different quantities. In this paper, we present a novel multi-view RGB-D based reconstruction method that tackles camera pose, lighting, albedo, and surface normal estimation via the utilization of a gradient signed distance field (gradient-SDF). The proposed method formulates the image rendering process using specific physically-based model(s) and optimizes the surface's quantities on the actual surface using its volumetric representation, as opposed to other works which estimate surface quantities only near the actual surface. To validate our method, we investigate two physically-based image formation models for natural light and point light source applications. The experimental results on synthetic and real-world datasets demonstrate that the proposed method can recover high-quality geometry of the surface more faithfully than the state-of-the-art and further improves the accuracy of estimated camera poses.

Yingye Xin, Xingxing Zuo, Dongyue Lu et al.

We present a real-time visual-inertial dense mapping method capable of performing incremental 3D mesh reconstruction with high quality using only sequential monocular images and inertial measurement unit (IMU) readings. 6-DoF camera poses are estimated by a robust feature-based visual-inertial odometry (VIO), which also generates noisy sparse 3D map points as a by-product. We propose a sparse point aided multi-view stereo neural network (SPA-MVSNet) that can effectively leverage the informative but noisy sparse points from the VIO system. The sparse depth from VIO is firstly completed by a single-view depth completion network. This dense depth map, although naturally limited in accuracy, is then used as a prior to guide our MVS network in the cost volume generation and regularization for accurate dense depth prediction. Predicted depth maps of keyframe images by the MVS network are incrementally fused into a global map using TSDF-Fusion. We extensively evaluate both the proposed SPA-MVSNet and the entire visual-inertial dense mapping system on several public datasets as well as our own dataset, demonstrating the system's impressive generalization capabilities and its ability to deliver high-quality 3D mesh reconstruction online. Our proposed dense mapping system achieves a 39.7% improvement in F-score over existing systems when evaluated on the challenging scenarios of the EuRoC dataset.

Yukai Ma, Jianbiao Mei, Xuemeng Yang et al.

Semantic Scene Completion (SSC) is pivotal in autonomous driving perception, frequently confronted with the complexities of weather and illumination changes. The long-term strategy involves fusing multi-modal information to bolster the system's robustness. Radar, increasingly utilized for 3D target detection, is gradually replacing LiDAR in autonomous driving applications, offering a robust sensing alternative. In this paper, we focus on the potential of 3D radar in semantic scene completion, pioneering cross-modal refinement techniques for improved robustness against weather and illumination changes, and enhancing SSC performance.Regarding model architecture, we propose a three-stage tight fusion approach on BEV to realize a fusion framework for point clouds and images. Based on this foundation, we designed three cross-modal distillation modules-CMRD, BRD, and PDD. Our approach enhances the performance in both radar-only (R-LiCROcc) and radar-camera (RC-LiCROcc) settings by distilling to them the rich semantic and structural information of the fused features of LiDAR and camera. Finally, our LC-Fusion (teacher model), R-LiCROcc and RC-LiCROcc achieve the best performance on the nuScenes-Occupancy dataset, with mIOU exceeding the baseline by 22.9%, 44.1%, and 15.5%, respectively. The project page is available at https://hr-zju.github.io/LiCROcc/.

Yuantai Zhang, Jiaqi Yang, Huajian Zeng et al.

Fast and reliable initialization is critical for monocular visual-inertial navigation systems (VINS), as it establishes the starting conditions for subsequent state estimation. Despite steady progress, most existing methods heavily rely on visual feature correspondences and require 3-4 seconds of sensory data for successful initialization, which limits their applicability and efficiency. With the advent of feed-forward 3D models that can directly predict point clouds from images, we revisit the visual-inertial initialization problem from a concise perspective. In this work, we propose a feature-free initialization framework that leverages up-to-scale point clouds predicted by a feed-forward 3D model, thereby obviating the need for visual feature tracking and estimation. This design substantially reduces system complexity and improves the reliability of initialization. Experiments on public datasets demonstrate that the proposed feature-free initialization method achieves the highest success rate, exceeding 90%, and significantly reduces the data duration required for successful initialization, typically to under 1.2 s. We further validate our method on a self-collected dataset covering various indoor and outdoor scenarios, demonstrating robust performance, particularly in visually degraded environments where existing methods often fail. The code and dataset are available at https://github.com/Yuantai-Z/FF-VIO-Init.

Huajian Zeng, Lingyun Chen, Jiaqi Yang et al.

Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An embodiment-agnostic interaction representation that captures this structure would make manipulation behaviors easier to validate and transfer across robots. We propose FlowHOI, a two-stage flow-matching framework that generates semantically grounded, temporally coherent HOI sequences, comprising hand poses, object poses, and hand-object contact states, conditioned on an egocentric observation, a language instruction, and a 3D Gaussian splatting (3DGS) scene reconstruction. We decouple geometry-centric grasping from semantics-centric manipulation, conditioning the latter on compact 3D scene tokens and employing a motion-text alignment loss to semantically ground the generated interactions in both the physical scene layout and the language instruction. To address the scarcity of high-fidelity HOI supervision, we introduce a reconstruction pipeline that recovers aligned hand-object trajectories and meshes from large-scale egocentric videos, yielding an HOI prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI representations to real-robot execution pipelines.

Han Li, Yukai Ma, Yaqing Gu et al.

We present a novel approach for metric dense depth estimation based on the fusion of a single-view image and a sparse, noisy Radar point cloud. The direct fusion of heterogeneous Radar and image data, or their encodings, tends to yield dense depth maps with significant artifacts, blurred boundaries, and suboptimal accuracy. To circumvent this issue, we learn to augment versatile and robust monocular depth prediction with the dense metric scale induced from sparse and noisy Radar data. We propose a Radar-Camera framework for highly accurate and fine-detailed dense depth estimation with four stages, including monocular depth prediction, global scale alignment of monocular depth with sparse Radar points, quasi-dense scale estimation through learning the association between Radar points and image patches, and local scale refinement of dense depth using a scale map learner. Our proposed method significantly outperforms the state-of-the-art Radar-Camera depth estimation methods by reducing the mean absolute error (MAE) of depth estimation by 25.6% and 40.2% on the challenging nuScenes dataset and our self-collected ZJU-4DRadarCam dataset, respectively. Our code and dataset will be released at \url{https://github.com/MMOCKING/RadarCam-Depth}.

Connor Lee, Matthew Anderson, Nikhil Raganathan et al.

We present the first publicly-available RGB-thermal dataset designed for aerial robotics operating in natural environments. Our dataset captures a variety of terrain across the United States, including rivers, lakes, coastlines, deserts, and forests, and consists of synchronized RGB, thermal, global positioning, and inertial data. We provide semantic segmentation annotations for 10 classes commonly encountered in natural settings in order to drive the development of perception algorithms robust to adverse weather and nighttime conditions. Using this dataset, we propose new and challenging benchmarks for thermal and RGB-thermal (RGB-T) semantic segmentation, RGB-T image translation, and motion tracking. We present extensive results using state-of-the-art methods and highlight the challenges posed by temporal and geographical domain shifts in our data. The dataset and accompanying code is available at https://github.com/aerorobotics/caltech-aerial-rgbt-dataset.

Huajian Zeng, Chaohua Yao, Yuantai Zhang et al.

Recovering world space 4D motion of two interacting hands from egocentric video is a fundamental capability for supervising robot policy learning, where wrist trajectories track the end-effector and finger articulations specify the grasp pose. Two major challenges arise in this setting: hands frequently leave the camera view for extended periods due to head motion, and persistent hand-object interactions cause severe occlusions of one or both hands. Existing methods uniformly condition on noisy hand motion observations without accounting for their per-frame reliability, leading to substantial performance degradation. Our key insight is that accurate world space hand motion estimation is tightly coupled with the quality of per-frame hand observations. To this end, we decompose the quality of hand motion observations extracted from an off-the-shelf hand pose estimator into four channels: wrist global translation and finger articulations for both hands. We propose StableHand, a quality-aware flow-matching framework conditioned on these four-channel quality signals, which are predicted by a learned quality network. We naturally incorporate the quality signals into the flow-matching process through a per-channel forward schedule, a quality-adjusted velocity target, AdaLN modulation of the DiT denoiser, and a quality-aware ODE initialization. This unified generative process preserves high-quality observations while reconstructing unreliable ones using a learned bimanual motion prior. Experiments on HOT3D and ARCTIC, two egocentric benchmarks featuring long missing-hand spans and persistent hand-object occlusions, show that StableHand achieves state-of-the-art performance across all reported metrics, reducing W-MPJPE by 20-25% compared to the strongest baseline, with the largest gains on heavily occluded ARCTIC sequences.

Han Li, Yukai Ma, Yuehao Huang et al.

Dense depth recovery is crucial in autonomous driving, serving as a foundational element for obstacle avoidance, 3D object detection, and local path planning. Adverse weather conditions, including haze, dust, rain, snow, and darkness, introduce significant challenges to accurate dense depth estimation, thereby posing substantial safety risks in autonomous driving. These challenges are particularly pronounced for traditional depth estimation methods that rely on short electromagnetic wave sensors, such as visible spectrum cameras and near-infrared LiDAR, due to their susceptibility to diffraction noise and occlusion in such environments. To fundamentally overcome this issue, we present a novel approach for robust metric depth estimation by fusing a millimeter-wave Radar and a monocular infrared thermal camera, which are capable of penetrating atmospheric particles and unaffected by lighting conditions. Our proposed Radar-Infrared fusion method achieves highly accurate and finely detailed dense depth estimation through three stages, including monocular depth prediction with global scale alignment, quasi-dense Radar augmentation by learning Radar-pixels correspondences, and local scale refinement of dense depth using a scale map learner. Our method achieves exceptional visual quality and accurate metric estimation by addressing the challenges of ambiguity and misalignment that arise from directly fusing multi-modal long-wave features. We evaluate the performance of our approach on the NTU4DRadLM dataset and our self-collected challenging ZJU-Multispectrum dataset. Especially noteworthy is the unprecedented robustness demonstrated by our proposed method in smoky scenarios. Our code will be released at \url{https://github.com/MMOCKING/RIDERS}.

Ruoyu Wang, Yukai Ma, Yi Yao et al.

Semantic Scene Completion (SSC) constitutes a pivotal element in autonomous driving perception systems, tasked with inferring the 3D semantic occupancy of a scene from sensory data. To improve accuracy, prior research has implemented various computationally demanding and memory-intensive 3D operations, imposing significant computational requirements on the platform during training and testing. This paper proposes L2COcc, a lightweight camera-centric SSC framework that also accommodates LiDAR inputs. With our proposed efficient voxel transformer (EVT) and cross-modal knowledge modules, including feature similarity distillation (FSD), TPV distillation (TPVD) and prediction alignment distillation (PAD), our method substantially reduce computational burden while maintaining high accuracy. The experimental evaluations demonstrate that our proposed method surpasses the current state-of-the-art vision-based SSC methods regarding accuracy on both the SemanticKITTI and SSCBench-KITTI-360 benchmarks, respectively. Additionally, our method is more lightweight, exhibiting a reduction in both memory consumption and inference time by over 23% compared to the current state-of-the-arts method. Code is available at our project page:https://studyingfufu.github.io/L2COcc/.

Abhishek Saroha, Huajian Zeng, Xingxing Zuo et al.

Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories remains challenging due to occlusions, fast motion, and the lack of explicit physical reasoning in existing generative models. We present EgoFlow, a flow-matching framework that synthesizes realistic and physically plausible trajectories conditioned on multimodal egocentric observations. EgoFlow employs a hybrid Mamba-Transformer-Perceiver architecture to jointly model temporal dynamics, scene geometry, and semantic intent, while a gradient-guided inference process enforces differentiable physical constraints such as collision avoidance and motion smoothness. This combination yields coherent and controllable motion generation without post-hoc filtering or additional supervision. Experiments on real-world datasets HD-EPIC, EgoExo4D, and HOT3D show that EgoFlow outperforms diffusion-based and transformer baselines in accuracy, generalization, and physical realism, reducing collision rates by up to 79%, and strong generalization to unseen scenes. Our results highlight the promise of flow-based generative modeling for scalable and physically grounded egocentric motion understanding.

Jiajun Lv, Kewei Hu, Jinhong Xu et al.

In this paper, we propose a highly accurate continuous-time trajectory estimation framework dedicated to SLAM (Simultaneous Localization and Mapping) applications, which enables fuse high-frequency and asynchronous sensor data effectively. We apply the proposed framework in a 3D LiDAR-inertial system for evaluations. The proposed method adopts a non-rigid registration method for continuous-time trajectory estimation and simultaneously removing the motion distortion in LiDAR scans. Additionally, we propose a two-state continuous-time trajectory correction method to efficiently and efficiently tackle the computationally-intractable global optimization problem when loop closure happens. We examine the accuracy of the proposed approach on several publicly available datasets and the data we collected. The experimental results indicate that the proposed method outperforms the discrete-time methods regarding accuracy especially when aggressive motion occurs. Furthermore, we open source our code at \url{https://github.com/APRIL-ZJU/clins} to benefit research community.

Jiajun Lv, Jinhong Xu, Kewei Hu et al.

Sensor calibration is the fundamental block for a multi-sensor fusion system. This paper presents an accurate and repeatable LiDAR-IMU calibration method (termed LI-Calib), to calibrate the 6-DOF extrinsic transformation between the 3D LiDAR and the Inertial Measurement Unit (IMU). % Regarding the high data capture rate for LiDAR and IMU sensors, LI-Calib adopts a continuous-time trajectory formulation based on B-Spline, which is more suitable for fusing high-rate or asynchronous measurements than discrete-time based approaches. % Additionally, LI-Calib decomposes the space into cells and identifies the planar segments for data association, which renders the calibration problem well-constrained in usual scenarios without any artificial targets. We validate the proposed calibration approach on both simulated and real-world experiments. The results demonstrate the high accuracy and good repeatability of the proposed method in common human-made scenarios. To benefit the research community, we open-source our code at \url{https://github.com/APRIL-ZJU/lidar_IMU_calib}

Xingxing Zuo, Pouya Samangouei, Yunwen Zhou et al.

Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this end, we present Foundation Model Embedded Gaussian Splatting (FMGS), which incorporates vision-language embeddings of foundation models into 3D Gaussian Splatting (GS). The key contribution of this work is an efficient method to reconstruct and represent 3D vision-language models. This is achieved by distilling feature maps generated from image-based foundation models into those rendered from our 3D model. To ensure high-quality rendering and fast training, we introduce a novel scene representation by integrating strengths from both GS and multi-resolution hash encodings (MHE). Our effective training procedure also introduces a pixel alignment loss that makes the rendered feature distance of the same semantic entities close, following the pixel-level semantic boundaries. Our results demonstrate remarkable multi-view semantic consistency, facilitating diverse downstream tasks, beating state-of-the-art methods by 10.2 percent on open-vocabulary language-based object detection, despite that we are 851X faster for inference. This research explores the intersection of vision, language, and 3D scene representation, paving the way for enhanced scene understanding in uncontrolled real-world environments. We plan to release the code on the project page.

Zeyu Jiang, Changqing Zhou, Xingxing Zuo et al.

Existing learning-based occupancy prediction methods rely on large-scale 3D annotations and generalize poorly across environments. We present FreeOcc, a training-free framework for open-vocabulary occupancy prediction from monocular or RGB-D sequences. Unlike prior approaches that require voxel-level supervision and ground-truth camera poses, FreeOcc operates without 3D annotations, pose ground truth, or any learning stage. FreeOcc incrementally builds a globally consistent occupancy map via a four-layer pipeline: a SLAM backbone estimates poses and sparse geometry; a geometrically consistent Gaussian update constructs dense 3D Gaussian maps; open-vocabulary semantics from off-the-shelf vision-language models are associated with Gaussian primitives; and a probabilistic Gaussian-to-occupancy projection produces dense voxel occupancy. Despite being entirely training-free and pose-agnostic, FreeOcc achieves over $2\times$ improvements in IoU and mIoU on EmbodiedOcc-ScanNet compared to prior self-supervised methods. We further introduce ReplicaOcc, a benchmark for indoor open-vocabulary occupancy prediction, and show that FreeOcc transfers zero-shot to novel environments, substantially outperforming both supervised and self-supervised baselines. Project page: https://the-masses.github.io/freeocc-web/.

Jens Naumann, Binbin Xu, Stefan Leutenegger et al.

We introduce a novel monocular visual odometry (VO) system, NeRF-VO, that integrates learning-based sparse visual odometry for low-latency camera tracking and a neural radiance scene representation for fine-detailed dense reconstruction and novel view synthesis. Our system initializes camera poses using sparse visual odometry and obtains view-dependent dense geometry priors from a monocular prediction network. We harmonize the scale of poses and dense geometry, treating them as supervisory cues to train a neural implicit scene representation. NeRF-VO demonstrates exceptional performance in both photometric and geometric fidelity of the scene representation by jointly optimizing a sliding window of keyframed poses and the underlying dense geometry, which is accomplished through training the radiance field with volume rendering. We surpass SOTA methods in pose estimation accuracy, novel view synthesis fidelity, and dense reconstruction quality across a variety of synthetic and real-world datasets while achieving a higher camera tracking frequency and consuming less GPU memory.

Hanfeng Wu, Xingxing Zuo, Stefan Leutenegger et al.

We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes. DyNFL processes LiDAR measurements from dynamic environments, accompanied by bounding boxes of moving objects, to construct an editable neural field. This field, comprising separately reconstructed static background and dynamic objects, allows users to modify viewpoints, adjust object positions, and seamlessly add or remove objects in the re-simulated scene. A key innovation of our method is the neural field composition technique, which effectively integrates reconstructed neural assets from various scenes through a ray drop test, accounting for occlusions and transparent surfaces. Our evaluation with both synthetic and real-world environments demonstrates that DyNFL substantially improves dynamic scene LiDAR simulation, offering a combination of physical fidelity and flexible editing capabilities.

Mengmeng Wang, Jiazheng Xing, Boyuan Jiang et al.

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing approaches tend to prioritize strong supervised performance at the expense of compromising the models' generalization capabilities during transfer. In this paper, we introduce a novel Multimodal, Multi-task CLIP adapting framework named \name to address these challenges, preserving both high supervised performance and robust transferability. Firstly, to enhance the individual modality architectures, we introduce multimodal adapters to both the visual and text branches. Specifically, we design a novel visual TED-Adapter, that performs global Temporal Enhancement and local temporal Difference modeling to improve the temporal representation capabilities of the visual encoder. Moreover, we adopt text encoder adapters to strengthen the learning of semantic label information. Secondly, we design a multi-task decoder with a rich set of supervisory signals to adeptly satisfy the need for strong supervised performance and generalization within a multimodal framework. Experimental results validate the efficacy of our approach, demonstrating exceptional performance in supervised learning while maintaining strong generalization in zero-shot scenarios.

Haoang Li, Xiangqi Meng, Xingxing Zuo et al.

Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many methods directly filter out dynamic objects, resulting in incomplete scene reconstruction and limited accuracy of camera localization. The other works express dynamic objects by point clouds, sparse joints, or coarse meshes, which fails to provide a photo-realistic representation. To overcome the above limitations, we propose a photo-realistic and geometry-aware RGB-D SLAM method by extending Gaussian splatting. Our method is composed of three main modules to 1) map the dynamic foreground including non-rigid humans and rigid items, 2) reconstruct the static background, and 3) localize the camera. To map the foreground, we focus on modeling the deformations and/or motions. We consider the shape priors of humans and exploit geometric and appearance constraints of humans and items. For background mapping, we design an optimization strategy between neighboring local maps by integrating appearance constraint into geometric alignment. As to camera localization, we leverage both static background and dynamic foreground to increase the observations for noise compensation. We explore the geometric and appearance constraints by associating 3D Gaussians with 2D optical flows and pixel patches. Experiments on various real-world datasets demonstrate that our method outperforms state-of-the-art approaches in terms of camera localization and scene representation. Source codes will be publicly available upon paper acceptance.

Xiaolei Lang, Yang Wang, Yukun Zhou et al.

Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-world tasks. However, scaling these systems remains difficult because collecting task-specific demonstrations is expensive and labor-intensive. Synthetic data, especially generated videos, offer a promising direction, but existing World Models (WMs) are not directly suitable for policy learning since they do not provide paired action trajectories. World-Action (WA) models partially address this by predicting actions with visual outputs, yet often lack strong video-action alignment, while two-stage pipelines that generate video first and then infer actions introduce inefficiency and error accumulation. To address these limitations, we propose VAG, a unified flow-matching-based dual-stream framework that jointly generates video and action under visual and language conditioning. By synchronizing denoising in both branches and using an adaptive 3D pooling mechanism to transfer compact global video context to the action branch, VAG improves cross-modal consistency during generation. Across both simulated and real-world settings, VAG produces aligned video-action pairs with competitive prediction quality, supports executable trajectory replay, and provides useful synthetic pretraining data that improves downstream policy generalization, indicating its potential as a practical world-action model for embodied data synthesis.

Xingxing Zuo, Nikhil Ranganathan, Connor Lee et al.

Monocular depth estimation (MDE) from thermal images is a crucial technology for robotic systems operating in challenging conditions such as fog, smoke, and low light. The limited availability of labeled thermal data constrains the generalization capabilities of thermal MDE models compared to foundational RGB MDE models, which benefit from datasets of millions of images across diverse scenarios. To address this challenge, we introduce a novel pipeline that enhances thermal MDE through knowledge distillation from a versatile RGB MDE model. Our approach features a confidence-aware distillation method that utilizes the predicted confidence of the RGB MDE to selectively strengthen the thermal MDE model, capitalizing on the strengths of the RGB model while mitigating its weaknesses. Our method significantly improves the accuracy of the thermal MDE, independent of the availability of labeled depth supervision, and greatly expands its applicability to new scenarios. In our experiments on new scenarios without labeled depth, the proposed confidence-aware distillation method reduces the absolute relative error of thermal MDE by 22.88\% compared to the baseline without distillation.

Yuhang Lin, Yijia Xie, Jiahong Xie et al.

Generating physically realistic humanoid-object interactions (HOI) is a fundamental challenge in robotics. Existing HOI generation approaches, such as diffusion-based models, often suffer from artifacts such as implausible contacts, penetrations, and unrealistic whole-body actions, which hinder successful execution in physical environments. To address these challenges, we introduce SimGenHOI, a unified framework that combines the strengths of generative modeling and reinforcement learning to produce controllable and physically plausible HOI. Our HOI generative model, based on Diffusion Transformers (DiT), predicts a set of key actions conditioned on text prompts, object geometry, sparse object waypoints, and the initial humanoid pose. These key actions capture essential interaction dynamics and are interpolated into smooth motion trajectories, naturally supporting long-horizon generation. To ensure physical realism, we design a contact-aware whole-body control policy trained with reinforcement learning, which tracks the generated motions while correcting artifacts such as penetration and foot sliding. Furthermore, we introduce a mutual fine-tuning strategy, where the generative model and the control policy iteratively refine each other, improving both motion realism and tracking robustness. Extensive experiments demonstrate that SimGenHOI generates realistic, diverse, and physically plausible humanoid-object interactions, achieving significantly higher tracking success rates in simulation and enabling long-horizon manipulation tasks. Code will be released upon acceptance on our project page: https://xingxingzuo.github.io/simgen_hoi.

Simon Schaefer, Juan D. Galvis, Xingxing Zuo et al.

We present a novel 3D shape completion framework that unifies multimodal conditioning, leveraging both 2D images and 3D partial scans through a latent diffusion model. Shapes are represented as Truncated Signed Distance Functions (TSDFs) and encoded into a discrete latent space jointly supervised by 2D and 3D cues, enabling efficient high-resolution processing while reducing GPU memory usage by 30\% compared to state-of-the-art methods. Our approach guides the generation process with flexible multimodal conditioning, ensuring consistent integration of 2D and 3D information from encoding to reconstruction. Our training strategy simulates realistic partial observations, avoiding assumptions about input structure and improving robustness in real-world scenarios. Leveraging our efficient latent space and multimodal conditioning, our model generalizes across object categories, outperforming class-specific models by 12\% and class-agnostic models by 47\% in $l_1$ reconstruction error, while producing more diverse, realistic, and high-fidelity completions than prior approaches.

Xingxing Zuo, Nan Yang, Nathaniel Merrill et al.

Incrementally recovering 3D dense structures from monocular videos is of paramount importance since it enables various robotics and AR applications. Feature volumes have recently been shown to enable efficient and accurate incremental dense reconstruction without the need to first estimate depth, but they are not able to achieve as high of a resolution as depth-based methods due to the large memory consumption of high-resolution feature volumes. This letter proposes a real-time feature volume-based dense reconstruction method that predicts TSDF (Truncated Signed Distance Function) values from a novel sparsified deep feature volume, which is able to achieve higher resolutions than previous feature volume-based methods, and is favorable in large-scale outdoor scenarios where the majority of voxels are empty. An uncertainty-aware multi-view stereo (MVS) network is leveraged to infer initial voxel locations of the physical surface in a sparse feature volume. Then for refining the recovered 3D geometry, deep features are attentively aggregated from multiview images at potential surface locations, and temporally fused. Besides achieving higher resolutions than before, our method is shown to produce more complete reconstructions with finer detail in many cases. Extensive evaluations on both public and self-collected datasets demonstrate a very competitive real-time reconstruction result for our method compared to state-of-the-art reconstruction methods in both indoor and outdoor settings.

Mengmeng Wang, Teli Ma, Xingxing Zuo et al.

3D LiDAR-based single object tracking (SOT) has gained increasing attention as it plays a crucial role in 3D applications such as autonomous driving. The central problem is how to learn a target-aware representation from the sparse and incomplete point clouds. In this paper, we propose a novel Correlation Pyramid Network (CorpNet) with a unified encoder and a motion-factorized decoder. Specifically, the encoder introduces multi-level self attentions and cross attentions in its main branch to enrich the template and search region features and realize their fusion and interaction, respectively. Additionally, considering the sparsity characteristics of the point clouds, we design a lateral correlation pyramid structure for the encoder to keep as many points as possible by integrating hierarchical correlated features. The output features of the search region from the encoder can be directly fed into the decoder for predicting target locations without any extra matcher. Moreover, in the decoder of CorpNet, we design a motion-factorized head to explicitly learn the different movement patterns of the up axis and the x-y plane together. Extensive experiments on two commonly-used datasets show our CorpNet achieves state-of-the-art results while running in real-time.

Yulin Yang, Patrick Geneva, Xingxing Zuo et al.

In this paper, we study in-depth the problem of online self-calibration for robust and accurate visual-inertial state estimation. In particular, we first perform a complete observability analysis for visual-inertial navigation systems (VINS) with full calibration of sensing parameters, including IMU and camera intrinsics and IMU-camera spatial-temporal extrinsic calibration, along with readout time of rolling shutter (RS) cameras (if used). We investigate different inertial model variants containing IMU intrinsic parameters that encompass most commonly used models for low-cost inertial sensors. The observability analysis results prove that VINS with full sensor calibration has four unobservable directions, corresponding to the system's global yaw and translation, while all sensor calibration parameters are observable given fully-excited 6-axis motion. Moreover, we, for the first time, identify primitive degenerate motions for IMU and camera intrinsic calibration. Each degenerate motion profile will cause a set of calibration parameters to be unobservable and any combination of these degenerate motions are still degenerate. Extensive Monte-Carlo simulations and real-world experiments are performed to validate both the observability analysis and identified degenerate motions, showing that online self-calibration improves system accuracy and robustness to calibration inaccuracies. We compare the proposed online self-calibration on commonly-used IMUs against the state-of-art offline calibration toolbox Kalibr, and show that the proposed system achieves better consistency and repeatability. Based on our analysis and experimental evaluations, we also provide practical guidelines for how to perform online IMU-camera sensor self-calibration.

Peidong Liu, Xingxing Zuo, Viktor Larsson et al.

Motion blur is one of the major challenges remaining for visual odometry methods. In low-light conditions where longer exposure times are necessary, motion blur can appear even for relatively slow camera motions. In this paper we present a novel hybrid visual odometry pipeline with direct approach that explicitly models and estimates the camera's local trajectory within the exposure time. This allows us to actively compensate for any motion blur that occurs due to the camera motion. In addition, we also contribute a novel benchmarking dataset for motion blur aware visual odometry. In experiments we show that by directly modeling the image formation process, we are able to improve robustness of the visual odometry, while keeping comparable accuracy as that for images without motion blur.

Xingxing Zuo, Nathaniel Merrill, Wei Li et al.

In this work, we present a lightweight, tightly-coupled deep depth network and visual-inertial odometry (VIO) system, which can provide accurate state estimates and dense depth maps of the immediate surroundings. Leveraging the proposed lightweight Conditional Variational Autoencoder (CVAE) for depth inference and encoding, we provide the network with previously marginalized sparse features from VIO to increase the accuracy of initial depth prediction and generalization capability. The compact encoded depth maps are then updated jointly with navigation states in a sliding window estimator in order to provide the dense local scene geometry. We additionally propose a novel method to obtain the CVAE's Jacobian which is shown to be more than an order of magnitude faster than previous works, and we additionally leverage First-Estimate Jacobian (FEJ) to avoid recalculation. As opposed to previous works relying on completely dense residuals, we propose to only provide sparse measurements to update the depth code and show through careful experimentation that our choice of sparse measurements and FEJs can still significantly improve the estimated depth maps. Our full system also exhibits state-of-the-art pose estimation accuracy, and we show that it can run in real-time with single-thread execution while utilizing GPU acceleration only for the network and code Jacobian.

Xingxing Zuo, Yulin Yang, Patrick Geneva et al.

Multi-sensor fusion of multi-modal measurements from commodity inertial, visual and LiDAR sensors to provide robust and accurate 6DOF pose estimation holds great potential in robotics and beyond. In this paper, building upon our prior work (i.e., LIC-Fusion), we develop a sliding-window filter based LiDAR-Inertial-Camera odometry with online spatiotemporal calibration (i.e., LIC-Fusion 2.0), which introduces a novel sliding-window plane-feature tracking for efficiently processing 3D LiDAR point clouds. In particular, after motion compensation for LiDAR points by leveraging IMU data, low-curvature planar points are extracted and tracked across the sliding window. A novel outlier rejection criterion is proposed in the plane-feature tracking for high-quality data association. Only the tracked planar points belonging to the same plane will be used for plane initialization, which makes the plane extraction efficient and robust. Moreover, we perform the observability analysis for the LiDAR-IMU subsystem and report the degenerate cases for spatiotemporal calibration using plane features. While the estimation consistency and identified degenerate motions are validated in Monte-Carlo simulations, different real-world experiments are also conducted to show that the proposed LIC-Fusion 2.0 outperforms its predecessor and other state-of-the-art methods.

Xingxing Zuo, Mingming Zhang, Mengmeng Wang et al.

To build commercial robots, skid-steering mechanical design is of increased popularity due to its manufacturing simplicity and unique mechanism. However, these also cause significant challenges on software and algorithm design, especially for the pose estimation (i.e., determining the robot's rotation and position) of skid-steering robots, since they change their orientation with an inevitable skid. To tackle this problem, we propose a probabilistic sliding-window estimator dedicated to skid-steering robots, using measurements from a monocular camera, the wheel encoders, and optionally an inertial measurement unit (IMU). Specifically, we explicitly model the kinematics of skid-steering robots by both track instantaneous centers of rotation (ICRs) and correction factors, which are capable of compensating for the complexity of track-to-terrain interaction, the imperfectness of mechanical design, terrain conditions and smoothness, etc. To prevent performance reduction in robots' long-term missions, the time- and location- varying kinematic parameters are estimated online along with pose estimation states in a tightly-coupled manner. More importantly, we conduct in-depth observability analysis for different sensors and design configurations in this paper, which provides us with theoretical tools in making the correct choice when building real commercial robots. In our experiments, we validate the proposed method by both simulation tests and real-world experiments, which demonstrate that our method outperforms competing methods by wide margins.

Xingxing Zuo, Mingming Zhang, Yiming Chen et al.

While visual localization or SLAM has witnessed great progress in past decades, when deploying it on a mobile robot in practice, few works have explicitly considered the kinematic (or dynamic) constraints of the real robotic system when designing state estimators. To promote the practical deployment of current state-of-the-art visual-inertial localization algorithms, in this work we propose a low-cost kinematics-constrained localization system particularly for a skid-steering mobile robot. In particular, we derive in a principle way the robot's kinematic constraints based on the instantaneous centers of rotation (ICR) model and integrate them in a tightly-coupled manner into the sliding-window bundle adjustment (BA)-based visual-inertial estimator. Because the ICR model parameters are time-varying due to, for example, track-to-terrain interaction and terrain roughness, we estimate these kinematic parameters online along with the navigation state. To this end, we perform in-depth the observability analysis and identify motion conditions under which the state/parameter estimation is viable. The proposed kinematics-constrained visual-inertial localization system has been validated extensively in different terrain scenarios.

Xingxing Zuo, Patrick Geneva, Woosik Lee et al.

This paper presents a tightly-coupled multi-sensor fusion algorithm termed LiDAR-inertial-camera fusion (LIC-Fusion), which efficiently fuses IMU measurements, sparse visual features, and extracted LiDAR points. In particular, the proposed LIC-Fusion performs online spatial and temporal sensor calibration between all three asynchronous sensors, in order to compensate for possible calibration variations. The key contribution is the optimal (up to linearization errors) multi-modal sensor fusion of detected and tracked sparse edge/surf feature points from LiDAR scans within an efficient MSCKF-based framework, alongside sparse visual feature observations and IMU readings. We perform extensive experiments in both indoor and outdoor environments, showing that the proposed LIC-Fusion outperforms the state-of-the-art visual-inertial odometry (VIO) and LiDAR odometry methods in terms of estimation accuracy and robustness to aggressive motions.

Mingming Zhang, Xingxing Zuo, Yiming Chen et al.

In this paper, we focus on motion estimation dedicated for non-holonomic ground robots, by probabilistically fusing measurements from the wheel odometer and exteroceptive sensors. For ground robots, the wheel odometer is widely used in pose estimation tasks, especially in applications under planar-scene based environments. However, since the wheel odometer only provides 2D motion estimates, it is extremely challenging to use that for performing accurate full 6D pose (3D position and 3D orientation) estimation. Traditional methods on 6D pose estimation either approximate sensor or motion models, at the cost of accuracy reduction, or rely on other sensors, e.g., inertial measurement unit (IMU), to provide complementary measurements. By contrast, in this paper, we propose a novel method to utilize the wheel odometer for 6D pose estimation, by modeling and utilizing motion manifold for ground robots. Our approach is probabilistically formulated and only requires the wheel odometer and an exteroceptive sensor (e.g., a camera). Specifically, our method i) formulates the motion manifold of ground robots by parametric representation, ii) performs manifold based 6D integration with the wheel odometer measurements only, and iii) re-parameterizes manifold equations periodically for error reduction. To demonstrate the effectiveness and applicability of the proposed algorithmic modules, we integrate that into a sliding-window pose estimator by using measurements from the wheel odometer and a monocular camera. By conducting extensive simulated and real-world experiments, we show that the proposed algorithm outperforms competing state-of-the-art algorithms by a significant margin in pose estimation accuracy, especially when deployed in complex large-scale real-world environments.

Xingxing Zuo, Xiaojia Xie, Yong Liu et al.

In this paper, we develop a robust efficient visual SLAM system that utilizes heterogeneous point and line features. By leveraging ORB-SLAM [1], the proposed system consists of stereo matching, frame tracking, local mapping, loop detection, and bundle adjustment of both point and line features. In particular, as the main theoretical contributions of this paper, we, for the first time, employ the orthonormal representation as the minimal parameterization to model line features along with point features in visual SLAM and analytically derive the Jacobians of the re-projection errors with respect to the line parameters, which significantly improves the SLAM solution. The proposed SLAM has been extensively tested in both synthetic and real-world experiments whose results demonstrate that the proposed system outperforms the state-of-the-art methods in various scenarios.