Ping Tan

Heng Li, Zhaopeng Cui, Shuaicheng Liu et al.

This paper proposes a deep recurrent Rotation Averaging Graph Optimizer (RAGO) for Multiple Rotation Averaging (MRA). Conventional optimization-based methods usually fail to produce accurate results due to corrupted and noisy relative measurements. Recent learning-based approaches regard MRA as a regression problem, while these methods are sensitive to initialization due to the gauge freedom problem. To handle these problems, we propose a learnable iterative graph optimizer minimizing a gauge-invariant cost function with an edge rectification strategy to mitigate the effect of inaccurate measurements. Our graph optimizer iteratively refines the global camera rotations by minimizing each node's single rotation objective function. Besides, our approach iteratively rectifies relative rotations to make them more consistent with the current camera orientations and observed relative rotations. Furthermore, we employ a gated recurrent unit to improve the result by tracing the temporal information of the cost graph. Our framework is a real-time learning-to-optimize rotation averaging graph optimizer with a tiny size deployed for real-world applications. RAGO outperforms previous traditional and deep methods on real-world and synthetic datasets. The code is available at https://github.com/sfu-gruvi-3dv/RAGO

Xiongfeng Peng, Zhihua Liu, Weiming Li et al.

Recent deep learning based visual simultaneous localization and mapping (SLAM) methods have made significant progress. However, how to make full use of visual information as well as better integrate with inertial measurement unit (IMU) in visual SLAM has potential research value. This paper proposes a novel deep SLAM network with dual visual factors. The basic idea is to integrate both photometric factor and re-projection factor into the end-to-end differentiable structure through multi-factor data association module. We show that the proposed network dynamically learns and adjusts the confidence maps of both visual factors and it can be further extended to include the IMU factors as well. Extensive experiments validate that our proposed method significantly outperforms the state-of-the-art methods on several public datasets, including TartanAir, EuRoC and ETH3D-SLAM. Specifically, when dynamically fusing the three factors together, the absolute trajectory error for both monocular and stereo configurations on EuRoC dataset has reduced by 45.3% and 36.2% respectively.

Weiyu Li, Rui Chen, Xuelin Chen et al.

It is inherently ambiguous to lift 2D results from pre-trained diffusion models to a 3D world for text-to-3D generation. 2D diffusion models solely learn view-agnostic priors and thus lack 3D knowledge during the lifting, leading to the multi-view inconsistency problem. We find that this problem primarily stems from geometric inconsistency, and avoiding misplaced geometric structures substantially mitigates the problem in the final outputs. Therefore, we improve the consistency by aligning the 2D geometric priors in diffusion models with well-defined 3D shapes during the lifting, addressing the vast majority of the problem. This is achieved by fine-tuning the 2D diffusion model to be viewpoint-aware and to produce view-specific coordinate maps of canonically oriented 3D objects. In our process, only coarse 3D information is used for aligning. This "coarse" alignment not only resolves the multi-view inconsistency in geometries but also retains the ability in 2D diffusion models to generate detailed and diversified high-quality objects unseen in the 3D datasets. Furthermore, our aligned geometric priors (AGP) are generic and can be seamlessly integrated into various state-of-the-art pipelines, obtaining high generalizability in terms of unseen shapes and visual appearance while greatly alleviating the multi-view inconsistency problem. Our method represents a new state-of-the-art performance with an 85+% consistency rate by human evaluation, while many previous methods are around 30%. Our project page is https://sweetdreamer3d.github.io/

Xiaotao Hu, Wei Yin, Mingkai Jia et al.

Recent successes in autoregressive (AR) generation models, such as the GPT series in natural language processing, have motivated efforts to replicate this success in visual tasks. Some works attempt to extend this approach to autonomous driving by building video-based world models capable of generating realistic future video sequences and predicting ego states. However, prior works tend to produce unsatisfactory results, as the classic GPT framework is designed to handle 1D contextual information, such as text, and lacks the inherent ability to model the spatial and temporal dynamics essential for video generation. In this paper, we present DrivingWorld, a GPT-style world model for autonomous driving, featuring several spatial-temporal fusion mechanisms. This design enables effective modeling of both spatial and temporal dynamics, facilitating high-fidelity, long-duration video generation. Specifically, we propose a next-state prediction strategy to model temporal coherence between consecutive frames and apply a next-token prediction strategy to capture spatial information within each frame. To further enhance generalization ability, we propose a novel masking strategy and reweighting strategy for token prediction to mitigate long-term drifting issues and enable precise control. Our work demonstrates the ability to produce high-fidelity and consistent video clips of over 40 seconds in duration, which is over 2 times longer than state-of-the-art driving world models. Experiments show that, in contrast to prior works, our method achieves superior visual quality and significantly more accurate controllable future video generation. Our code is available at https://github.com/YvanYin/DrivingWorld.

Sicong Tang, Guangyuan Wang, Qing Ran et al.

We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1 to 6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.

Xiaodong Gu, Weihao Yuan, Heng Li et al.

Neural implicit surface reconstruction has become a new trend in reconstructing a detailed 3D shape from images. In previous methods, however, the 3D scene is only encoded by the MLPs which do not have an explicit 3D structure. To better represent 3D shapes, we introduce a volume encoding to explicitly encode the spatial information. We further design hierarchical volumes to encode the scene structures in multiple scales. The high-resolution volumes capture the high-frequency geometry details since spatially varying features could be learned from different 3D points, while the low-resolution volumes enforce the spatial consistency to keep the shape smooth since adjacent locations possess the same low-resolution feature. In addition, we adopt a sparse structure to reduce the memory consumption at high-resolution volumes, and two regularization terms to enhance results smoothness. This hierarchical volume encoding could be appended to any implicit surface reconstruction method as a plug-and-play module, and can generate a smooth and clean reconstruction with more details. Superior performance is demonstrated in DTU, EPFL, and BlendedMVS datasets with significant improvement on the standard metrics.

Mingkai Jia, Wei Yin, Xiaotao Hu et al.

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruction quality, however, there still exists a large gap between VQ-VAEs and VAEs. To narrow this gap, we propose MGVQ, a novel method to augment the representation capability of discrete codebooks, facilitating easier optimization for codebooks and minimizing information loss, thereby enhancing reconstruction quality. Specifically, we propose to retain the latent dimension to preserve encoded features and incorporate a set of sub-codebooks for quantization. Furthermore, we construct comprehensive zero-shot benchmarks featuring resolutions of 512p and 2k to evaluate the reconstruction performance of existing methods rigorously. MGVQ achieves the state-of-the-art performance on both ImageNet and 8 zero-shot benchmarks across all VQ-VAEs. Notably, compared with SD-VAE, we outperform them on ImageNet significantly, with rFID 0.49 v.s. 0.91, and achieve superior PSNR on all zero-shot benchmarks. These results highlight the superiority of MGVQ in reconstruction and pave the way for preserving fidelity in HD image processing tasks. Code will be publicly available at https://github.com/MKJia/MGVQ.

Mingkai Jia, Mingxiao Li, Liaoyuan Fan et al.

Recent advances in visual generation have highlighted the rise of Latent Generative Models (LGMs), which rely on effective visual tokenizers to bridge pixels and semantics. However, existing tokenizers are typically trained from scratch and struggle to balance semantic representation and reconstruction fidelity, particularly in high-dimensional latent spaces. In this work, we introduce DINO-Tok, a DINO-based visual tokenizer that unifies hierarchical representations into an information-complete latent space. By integrating shallow features that retain fine-grained details with deep features encoding global semantics, DINO-Tok effectively bridges pretrained representations and visual generation. We further analyze the challenges of vector quantization (VQ) in this high-dimensional space, where key information is often lost and codebook collapse occurs. We thus propose a global PCA reweighting mechanism to stabilize VQ and preserve essential information across dimensions. On ImageNet 256$\times$256, DINO-Tok achieves state-of-the-art reconstruction performance, reaching 28.54 PSNR for autoencoding and 23.98 PSNR for VQ-based modeling, significantly outperforming prior tokenizers and comparable to billion-level data trained models (such as Hunyuan and Wan). These results demonstrate that adapting powerful pretrained vision models like DINO for tokenization enables semantically aligned and high-fidelity latent representations, enabling next-generation visual generative models. Code will be publicly available at https://github.com/MKJia/DINO-Tok.

Lizhe Liu, Xiaohao Chen, Siyu Zhu et al.

Modern deep-learning-based lane detection methods are successful in most scenarios but struggling for lane lines with complex topologies. In this work, we propose CondLaneNet, a novel top-to-down lane detection framework that detects the lane instances first and then dynamically predicts the line shape for each instance. Aiming to resolve lane instance-level discrimination problem, we introduce a conditional lane detection strategy based on conditional convolution and row-wise formulation. Further, we design the Recurrent Instance Module(RIM) to overcome the problem of detecting lane lines with complex topologies such as dense lines and fork lines. Benefit from the end-to-end pipeline which requires little post-process, our method has real-time efficiency. We extensively evaluate our method on three benchmarks of lane detection. Results show that our method achieves state-of-the-art performance on all three benchmark datasets. Moreover, our method has the coexistence of accuracy and efficiency, e.g. a 78.14 F1 score and 220 FPS on CULane. Our code is available at https://github.com/aliyun/conditional-lane-detection.

Ziyuan Liu, Wei Liu, Yuzhe Qin et al.

In this paper, we propose a cloud-based benchmark for robotic grasping and manipulation, called the OCRTOC benchmark. The benchmark focuses on the object rearrangement problem, specifically table organization tasks. We provide a set of identical real robot setups and facilitate remote experiments of standardized table organization scenarios in varying difficulties. In this workflow, users upload their solutions to our remote server and their code is executed on the real robot setups and scored automatically. After each execution, the OCRTOC team resets the experimental setup manually. We also provide a simulation environment that researchers can use to develop and test their solutions. With the OCRTOC benchmark, we aim to lower the barrier of conducting reproducible research on robotic grasping and manipulation and accelerate progress in this field. Executing standardized scenarios on identical real robot setups allows us to quantify algorithm performances and achieve fair comparisons. Using this benchmark we held a competition in the 2020 International Conference on Intelligence Robots and Systems (IROS 2020). In total, 59 teams took part in this competition worldwide. We present the results and our observations of the 2020 competition, and discuss our adjustments and improvements for the upcoming OCRTOC 2021 competition. The homepage of the OCRTOC competition is www.ocrtoc.org, and the OCRTOC software package is available at https://github.com/OCRTOC/OCRTOC_software_package.

Shitao Tang, Chengzhou Tang, Rui Huang et al.

Camera localization aims to estimate 6 DoF camera poses from RGB images. Traditional methods detect and match interest points between a query image and a pre-built 3D model. Recent learning-based approaches encode scene structures into a specific convolutional neural network (CNN) and thus are able to predict dense coordinates from RGB images. However, most of them require re-training or re-adaption for a new scene and have difficulties in handling large-scale scenes due to limited network capacity. We present a new method for scene agnostic camera localization using dense scene matching (DSM), where a cost volume is constructed between a query image and a scene. The cost volume and the corresponding coordinates are processed by a CNN to predict dense coordinates. Camera poses can then be solved by PnP algorithms. In addition, our method can be extended to temporal domain, which leads to extra performance boost during testing time. Our scene-agnostic approach achieves comparable accuracy as the existing scene-specific approaches, such as KFNet, on the 7scenes and Cambridge benchmark. This approach also remarkably outperforms state-of-the-art scene-agnostic dense coordinate regression network SANet. The Code is available at https://github.com/Tangshitao/Dense-Scene-Matching.

Rakesh Shrestha, Zhiwen Fan, Qingkun Su et al.

Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation process. These color image semantics only implicitly encode 3D information, potentially limiting the accuracy of the generated shapes. In this paper we propose a multi-view mesh generation method which incorporates geometry information explicitly by using the features from intermediate depth representations of multi-view stereo and regularizing the 3D shapes against these depth images. First, our system predicts a coarse 3D volume from the color images by probabilistically merging voxel occupancy grids from the prediction of individual views. Then the depth images from multi-view stereo along with the rendered depth images of the coarse shape are used as a contrastive input whose features guide the refinement of the coarse shape through a series of graph convolution networks. Notably, we achieve superior results than state-of-the-art multi-view shape generation methods with 34% decrease in Chamfer distance to ground truth and 14% increase in F1-score on ShapeNet dataset.Our source code is available at https://git.io/Jmalg

Sicong Tang, Feitong Tan, Kelvin Cheng et al.

This paper presents a neural network to estimate a detailed depth map of the foreground human in a single RGB image. The result captures geometry details such as cloth wrinkles, which are important in visualization applications. To achieve this goal, we separate the depth map into a smooth base shape and a residual detail shape and design a network with two branches to regress them respectively. We design a training strategy to ensure both base and detail shapes can be faithfully learned by the corresponding network branches. Furthermore, we introduce a novel network layer to fuse a rough depth map and surface normals to further improve the final result. Quantitative comparison with fused `ground truth' captured by real depth cameras and qualitative examples on unconstrained Internet images demonstrate the strength of the proposed method. The code is available at https://github.com/sfu-gruvi-3dv/deep_human.

Runyi Yu, Yinhuai Wang, Qihan Zhao et al.

We address a fundamental challenge in Reinforcement Learning from Interaction Demonstration (RLID): demonstration noise and coverage limitations. While existing data collection approaches provide valuable interaction demonstrations, they often yield sparse, disconnected, and noisy trajectories that fail to capture the full spectrum of possible skill variations and transitions. Our key insight is that despite noisy and sparse demonstrations, there exist infinite physically feasible trajectories that naturally bridge between demonstrated skills or emerge from their neighboring states, forming a continuous space of possible skill variations and transitions. Building upon this insight, we present two data augmentation techniques: a Stitched Trajectory Graph (STG) that discovers potential transitions between demonstration skills, and a State Transition Field (STF) that establishes unique connections for arbitrary states within the demonstration neighborhood. To enable effective RLID with augmented data, we develop an Adaptive Trajectory Sampling (ATS) strategy for dynamic curriculum generation and a historical encoding mechanism for memory-dependent skill learning. Our approach enables robust skill acquisition that significantly generalizes beyond the reference demonstrations. Extensive experiments across diverse interaction tasks demonstrate substantial improvements over state-of-the-art methods in terms of convergence stability, generalization capability, and recovery robustness.

Junyuan Deng, Wei Yin, Xiaoyang Guo et al.

In this paper, we present DM-Calib, a diffusion-based approach for estimating pinhole camera intrinsic parameters from a single input image. Monocular camera calibration is essential for many 3D vision tasks. However, most existing methods depend on handcrafted assumptions or are constrained by limited training data, resulting in poor generalization across diverse real-world images. Recent advancements in stable diffusion models, trained on massive data, have shown the ability to generate high-quality images with varied characteristics. Emerging evidence indicates that these models implicitly capture the relationship between camera focal length and image content. Building on this insight, we explore how to leverage the powerful priors of diffusion models for monocular pinhole camera calibration. Specifically, we introduce a new image-based representation, termed Camera Image, which losslessly encodes the numerical camera intrinsics and integrates seamlessly with the diffusion framework. Using this representation, we reformulate the problem of estimating camera intrinsics as the generation of a dense Camera Image conditioned on an input image. By fine-tuning a stable diffusion model to generate a Camera Image from a single RGB input, we can extract camera intrinsics via a RANSAC operation. We further demonstrate that our monocular calibration method enhances performance across various 3D tasks, including zero-shot metric depth estimation, 3D metrology, pose estimation and sparse-view reconstruction. Extensive experiments on multiple public datasets show that our approach significantly outperforms baselines and provides broad benefits to 3D vision tasks.

Xiangyue Liu, Kunming Luo, Heng Li et al.

We introduce GaussianAvatar-Editor, an innovative framework for text-driven editing of animatable Gaussian head avatars that can be fully controlled in expression, pose, and viewpoint. Unlike static 3D Gaussian editing, editing animatable 4D Gaussian avatars presents challenges related to motion occlusion and spatial-temporal inconsistency. To address these issues, we propose the Weighted Alpha Blending Equation (WABE). This function enhances the blending weight of visible Gaussians while suppressing the influence on non-visible Gaussians, effectively handling motion occlusion during editing. Furthermore, to improve editing quality and ensure 4D consistency, we incorporate conditional adversarial learning into the editing process. This strategy helps to refine the edited results and maintain consistency throughout the animation. By integrating these methods, our GaussianAvatar-Editor achieves photorealistic and consistent results in animatable 4D Gaussian editing. We conduct comprehensive experiments across various subjects to validate the effectiveness of our proposed techniques, which demonstrates the superiority of our approach over existing methods. More results and code are available at: [Project Link](https://xiangyueliu.github.io/GaussianAvatar-Editor/).

Hongyu Yan, Kunming Luo, Weiyu Li et al.

3D characters play a crucial role in our daily entertainment. To improve the efficiency of 3D character modeling, recent image-based methods use two separate models to achieve pose standardization and 3D reconstruction of the A-pose character. However, these methods are prone to generating distorted and degraded images in the pose standardization stage due to self-occlusion and viewpoints, which further affects the geometric quality of the subsequent reconstruction process. To tackle these problems, we propose PoseMaster, an end-to-end controllable 3D character generation framework. Specifically, we unify pose transformation and 3D character generation into a flow-based 3D native generation framework. To achieve accurate arbitrary-pose control, we propose to leverage the 3D body bones existing in the skeleton of an animatable character as the pose condition. Furthermore, considering the specificity of multi-condition control, we randomly empty the pose condition and the image condition during training to improve the effectiveness and generalizability of pose control. Finally, we create a high-quality pose-control dataset derived from realistic character animation data to make the model learning the implicit relationships between skeleton and skinning weights. Extensive experiments show that PoseMaster outperforms current state-of-the-art techniques in both qualitative and quantitative evaluations for A-pose character generation while demonstrating its powerful ability to achieve precise control for arbitrary poses.

Wentian Qu, Chenyu Meng, Heng Li et al.

Object pose estimation, crucial in computer vision and robotics applications, faces challenges with the diversity of unseen categories. We propose a zero-shot method to achieve category-level 6-DOF object pose estimation, which exploits both 2D and 3D universal features of input RGB-D image to establish semantic similarity-based correspondences and can be extended to unseen categories without additional model fine-tuning. Our method begins with combining efficient 2D universal features to find sparse correspondences between intra-category objects and gets initial coarse pose. To handle the correspondence degradation of 2D universal features if the pose deviates much from the target pose, we use an iterative strategy to optimize the pose. Subsequently, to resolve pose ambiguities due to shape differences between intra-category objects, the coarse pose is refined by optimizing with dense alignment constraint of 3D universal features. Our method outperforms previous methods on the REAL275 and Wild6D benchmarks for unseen categories.

Yuan Dong, Chuan Fang, Liefeng Bo et al.

Panoramic image enables deeper understanding and more holistic perception of $360^\circ$ surrounding environment, which can naturally encode enriched scene context information compared to standard perspective image. Previous work has made lots of effort to solve the scene understanding task in a bottom-up form, thus each sub-task is processed separately and few correlations are explored in this procedure. In this paper, we propose a novel method using depth prior for holistic indoor scene understanding which recovers the objects' shapes, oriented bounding boxes and the 3D room layout simultaneously from a single panorama. In order to fully utilize the rich context information, we design a transformer-based context module to predict the representation and relationship among each component of the scene. In addition, we introduce a real-world dataset for scene understanding, including photo-realistic panoramas, high-fidelity depth images, accurately annotated room layouts, and oriented object bounding boxes and shapes. Experiments on the synthetic and real-world datasets demonstrate that our method outperforms previous panoramic scene understanding methods in terms of both layout estimation and 3D object detection.

Zhiwen Fan, Lingjie Zhu, Honghua Li et al.

Access to large and diverse computer-aided design (CAD) drawings is critical for developing symbol spotting algorithms. In this paper, we present FloorPlanCAD, a large-scale real-world CAD drawing dataset containing over 10,000 floor plans, ranging from residential to commercial buildings. CAD drawings in the dataset are all represented as vector graphics, which enable us to provide line-grained annotations of 30 object categories. Equipped by such annotations, we introduce the task of panoptic symbol spotting, which requires to spot not only instances of countable things, but also the semantic of uncountable stuff. Aiming to solve this task, we propose a novel method by combining Graph Convolutional Networks (GCNs) with Convolutional Neural Networks (CNNs), which captures both non-Euclidean and Euclidean features and can be trained end-to-end. The proposed CNN-GCN method achieved state-of-the-art (SOTA) performance on the task of semantic symbol spotting, and help us build a baseline network for the panoptic symbol spotting task. Our contributions are three-fold: 1) to the best of our knowledge, the presented CAD drawing dataset is the first of its kind; 2) the panoptic symbol spotting task considers the spotting of both thing instances and stuff semantic as one recognition problem; and 3) we presented a baseline solution to the panoptic symbol spotting task based on a novel CNN-GCN method, which achieved SOTA performance on semantic symbol spotting. We believe that these contributions will boost research in related areas.

Weihao Yuan, Yazhan Zhang, Bingkun Wu et al.

Self-supervised learning for depth estimation possesses several advantages over supervised learning. The benefits of no need for ground-truth depth, online fine-tuning, and better generalization with unlimited data attract researchers to seek self-supervised solutions. In this work, we propose a new self-supervised framework for stereo matching utilizing multiple images captured at aligned camera positions. A cross photometric loss, an uncertainty-aware mutual-supervision loss, and a new smoothness loss are introduced to optimize the network in learning disparity maps end-to-end without ground-truth depth information. To train this framework, we build a new multiscopic dataset consisting of synthetic images rendered by 3D engines and real images captured by real cameras. After being trained with only the synthetic images, our network can perform well in unseen outdoor scenes. Our experiment shows that our model obtains better disparity maps than previous unsupervised methods on the KITTI dataset and is comparable to supervised methods when generalized to unseen data. Our source code and dataset are available at https://sites.google.com/view/multiscopic.

Ziqian Bai, Zhaopeng Cui, Xiaoming Liu et al.

This paper presents a method for riggable 3D face reconstruction from monocular images, which jointly estimates a personalized face rig and per-image parameters including expressions, poses, and illuminations. To achieve this goal, we design an end-to-end trainable network embedded with a differentiable in-network optimization. The network first parameterizes the face rig as a compact latent code with a neural decoder, and then estimates the latent code as well as per-image parameters via a learnable optimization. By estimating a personalized face rig, our method goes beyond static reconstructions and enables downstream applications such as video retargeting. In-network optimization explicitly enforces constraints derived from the first principles, thus introduces additional priors than regression-based methods. Finally, data-driven priors from deep learning are utilized to constrain the ill-posed monocular setting and ease the optimization difficulty. Experiments demonstrate that our method achieves SOTA reconstruction accuracy, reasonable robustness and generalization ability, and supports standard face rig applications.

Feitong Tan, Danhang Tang, Mingsong Dou et al.

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot handle large motion or visually ambiguous body parts, e.g., left vs. right hand. In contrast, we propose a deep learning framework that maps each pixel to a feature space, where the feature distances reflect the geodesic distances among pixels as if they were projected onto the surface of a 3D human scan. To this end, we introduce novel loss functions to push features apart according to their geodesic distances on the surface. Without any semantic annotation, the proposed embeddings automatically learn to differentiate visually similar parts and align different subjects into an unified feature space. Extensive experiments show that the learned embeddings can produce accurate correspondences between images with remarkable generalization capabilities on both intra and inter subjects.

Rui Huang, Chuan Fang, Kejie Qiu et al.

Augmented reality (AR) has gained increasingly attention from both research and industry communities. By overlaying digital information and content onto the physical world, AR enables users to experience the world in a more informative and efficient manner. As a major building block for AR systems, localization aims at determining the device's pose from a pre-built "map" consisting of visual and depth information in a known environment. While the localization problem has been widely studied in the literature, the "map" for AR systems is rarely discussed. In this paper, we introduce the AR Map for a specific scene to be composed of 1) color images with 6-DOF poses; 2) dense depth maps for each image and 3) a complete point cloud map. We then propose an efficient end-to-end solution to generating and evaluating AR Maps. Firstly, for efficient data capture, a backpack scanning device is presented with a unified calibration pipeline. Secondly, we propose an AR mapping pipeline which takes the input from the scanning device and produces accurate AR Maps. Finally, we present an approach to evaluating the accuracy of AR Maps with the help of the highly accurate reconstruction result from a high-end laser scanner. To the best of our knowledge, it is the first time to present an end-to-end solution to efficient and accurate mapping for AR applications.

Kejie Qiu, Shenzhou Chen, Jiahui Zhang et al.

Accurate localization is fundamental to a variety of applications, such as navigation, robotics, autonomous driving, and Augmented Reality (AR). Different from incremental localization, global localization has no drift caused by error accumulation, which is desired in many application scenarios. In addition to GPS used in the open air, 3D maps are also widely used as alternative global localization references. In this paper, we propose a compact 3D map-based global localization system using a low-cost monocular camera and an IMU (Inertial Measurement Unit). The proposed compact map consists of two types of simplified elements with multiple semantic labels, which is well adaptive to various man-made environments like urban environments. Also, semantic edge features are used for the key image-map registration, which is robust against occlusion and long-term appearance changes in the environments. To further improve the localization performance, the key semantic edge alignment is formulated as an optimization problem based on initial poses predicted by an independent VIO (Visual-Inertial Odometry) module. The localization system is realized with modular design in real time. We evaluate the localization accuracy through real-world experimental results compared with ground truth, long-term localization performance is also demonstrated.

Feitong Tan, Hao Zhu, Zhaopeng Cui et al.

Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data. This paper presents a self-supervised method that can be trained on YouTube videos without known depth, which makes training data collection simple and improves the generalization of the learned network. The self-supervised learning is achieved by minimizing a photo-consistency loss, which is evaluated between a video frame and its neighboring frames warped according to the estimated depth and the 3D non-rigid motion of the human body. To solve this non-rigid motion, we first estimate a rough SMPL model at each video frame and compute the non-rigid body motion accordingly, which enables self-supervised learning on estimating the shape details. Experiments demonstrate that our method enjoys better generalization and performs much better on data in the wild.

Chengzhou Tang, Lu Yuan, Ping Tan

We study the energy minimization problem in low-level vision tasks from a novel perspective. We replace the heuristic regularization term with a learnable subspace constraint, and preserve the data term to exploit domain knowledge derived from the first principle of a task. This learning subspace minimization (LSM) framework unifies the network structures and the parameters for many low-level vision tasks, which allows us to train a single network for multiple tasks simultaneously with completely shared parameters, and even generalizes the trained network to an unseen task as long as its data term can be formulated. We demonstrate our LSM framework on four low-level tasks including interactive image segmentation, video segmentation, stereo matching, and optical flow, and validate the network on various datasets. The experiments show that the proposed LSM generates state-of-the-art results with smaller model size, faster training convergence, and real-time inference.

Lei Li, Siyu Zhu, Hongbo Fu et al.

In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.

Wenqi Shao, Shitao Tang, Xingang Pan et al.

Convolutional Neural Networks (CNNs) are typically constructed by stacking multiple building blocks, each of which contains a normalization layer such as batch normalization (BN) and a rectified linear function such as ReLU. However, this work shows that the combination of normalization and rectified linear function leads to inhibited channels, which have small magnitude and contribute little to the learned feature representation, impeding the generalization ability of CNNs. Unlike prior arts that simply removed the inhibited channels, we propose to "wake them up" during training by designing a novel neural building block, termed Channel Equilibrium (CE) block, which enables channels at the same layer to contribute equally to the learned representation. We show that CE is able to prevent inhibited channels both empirically and theoretically. CE has several appealing benefits. (1) It can be integrated into many advanced CNN architectures such as ResNet and MobileNet, outperforming their original networks. (2) CE has an interesting connection with the Nash Equilibrium, a well-known solution of a non-cooperative game. (3) Extensive experiments show that CE achieves state-of-the-art performance on various challenging benchmarks such as ImageNet and COCO.

Qian Zhang, Wei Feng, Liang Wan et al.

This paper studies a new problem, namely active lighting recurrence (ALR) that physically relocalizes a light source to reproduce the lighting condition from single reference image for a same scene, which may suffer from fine-grained changes during twice observations. ALR is of great importance for fine-grained visual inspection and change detection, because some phenomena or minute changes can only be clearly observed under particular lighting conditions. Therefore, effective ALR should be able to online navigate a light source toward the target pose, which is challenging due to the complexity and diversity of real-world lighting and imaging processes. To this end, we propose to use the simple parallel lighting as an analogy model and based on Lambertian law to compose an instant navigation ball for this purpose. We theoretically prove the feasibility, i.e., equivalence and convergence, of this ALR approach for realistic near point light source and small near surface light source. Besides, we also theoretically prove the invariance of our ALR approach to the ambiguity of normal and lighting decomposition. The effectiveness and superiority of the proposed approach have been verified by both extensive quantitative experiments and challenging real-world tasks on fine-grained change detection of cultural heritages. We also validate the generality of our approach to non-Lambertian scenes.

Min Li, Zhenglong Zhou, Zhe Wu et al.

We present a method to capture both 3D shape and spatially varying reflectance with a multi-view photometric stereo (MVPS) technique that works for general isotropic materials. Our algorithm is suitable for perspective cameras and nearby point light sources. Our data capture setup is simple, which consists of only a digital camera, some LED lights, and an optional automatic turntable. From a single viewpoint, we use a set of photometric stereo images to identify surface points with the same distance to the camera. We collect this information from multiple viewpoints and combine it with structure-from-motion to obtain a precise reconstruction of the complete 3D shape. The spatially varying isotropic bidirectional reflectance distribution function (BRDF) is captured by simultaneously inferring a set of basis BRDFs and their mixing weights at each surface point. In experiments, we demonstrate our algorithm with two different setups: a studio setup for highest precision and a desktop setup for best usability. According to our experiments, under the studio setting, the captured shapes are accurate to 0.5 millimeters and the captured reflectance has a relative root-mean-square error (RMSE) of 9%. We also quantitatively evaluate state-of-the-art MVPS on a newly collected benchmark dataset, which is publicly available for inspiring future research.

Xiaodong Gu, Zhiwen Fan, Zuozhuo Dai et al.

The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity. These methods are limited when high-resolution outputs are needed since the memory and time costs grow cubically as the volume resolution increases. In this paper, we propose a both memory and time efficient cost volume formulation that is complementary to existing multi-view stereo and stereo matching approaches based on 3D cost volumes. First, the proposed cost volume is built upon a standard feature pyramid encoding geometry and context at gradually finer scales. Then, we can narrow the depth (or disparity) range of each stage by the depth (or disparity) map from the previous stage. With gradually higher cost volume resolution and adaptive adjustment of depth (or disparity) intervals, the output is recovered in a coarser to fine manner. We apply the cascade cost volume to the representative MVS-Net, and obtain a 23.1% improvement on DTU benchmark (1st place), with 50.6% and 74.2% reduction in GPU memory and run-time. It is also the state-of-the-art learning-based method on Tanks and Temples benchmark. The statistics of accuracy, run-time and GPU memory on other representative stereo CNNs also validate the effectiveness of our proposed method.

Renjiao Yi, Ping Tan, Stephen Lin

We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos online, which exhibit large illumination variations that make them suitable for training of reflectance separation and can facilitate object-level decomposition. The main contribution of our approach is a proposed image representation based on local color distributions that allows training to be insensitive to the local misalignments of multi-view images. In addition, we present a new guidance cue for unsupervised training that exploits synergy between highlight separation and intrinsic image decomposition. Over a broad range of objects, our technique is shown to yield state-of-the-art results for both of these tasks.

Jie Tang, Fei-Peng Tian, Wei Feng et al.

Dense depth perception is critical for autonomous driving and other robotics applications. However, modern LiDAR sensors only provide sparse depth measurement. It is thus necessary to complete the sparse LiDAR data, where a synchronized guidance RGB image is often used to facilitate this completion. Many neural networks have been designed for this task. However, they often naïvely fuse the LiDAR data and RGB image information by performing feature concatenation or element-wise addition. Inspired by the guided image filtering, we design a novel guided network to predict kernel weights from the guidance image. These predicted kernels are then applied to extract the depth image features. In this way, our network generates content-dependent and spatially-variant kernels for multi-modal feature fusion. Dynamically generated spatially-variant kernels could lead to prohibitive GPU memory consumption and computation overhead. We further design a convolution factorization to reduce computation and memory consumption. The GPU memory reduction makes it possible for feature fusion to work in multi-stage scheme. We conduct comprehensive experiments to verify our method on real-world outdoor, indoor and synthetic datasets. Our method produces strong results. It outperforms state-of-the-art methods on the NYUv2 dataset and ranks 1st on the KITTI depth completion benchmark at the time of submission. It also presents strong generalization capability under different 3D point densities, various lighting and weather conditions as well as cross-dataset evaluations. The code will be released for reproduction.

Zuozhuo Dai, Mingqiang Chen, Xiaodong Gu et al.

Since the person re-identification task often suffers from the problem of pose changes and occlusions, some attentive local features are often suppressed when training CNNs. In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch. The global branch encodes the global salient representations. Meanwhile, the feature dropping branch consists of an attentive feature learning module called Batch DropBlock, which randomly drops the same region of all input feature maps in a batch to reinforce the attentive feature learning of local regions. The network then concatenates features from both branches and provides a more comprehensive and spatially distributed feature representation. Albeit simple, our method achieves state-of-the-art on person re-identification and it is also applicable to general metric learning tasks. For instance, we achieve 76.4% Rank-1 accuracy on the CUHK03-Detect dataset and 83.0% Recall-1 score on the Stanford Online Products dataset, outperforming the existing works by a large margin (more than 6%).

Chengzhou Tang, Ping Tan

This paper introduces a network architecture to solve the structure-from-motion (SfM) problem via feature-metric bundle adjustment (BA), which explicitly enforces multi-view geometry constraints in the form of feature-metric error. The whole pipeline is differentiable so that the network can learn suitable features that make the BA problem more tractable. Furthermore, this work introduces a novel depth parameterization to recover dense per-pixel depth. The network first generates several basis depth maps according to the input image and optimizes the final depth as a linear combination of these basis depth maps via feature-metric BA. The basis depth maps generator is also learned via end-to-end training. The whole system nicely combines domain knowledge (i.e. hard-coded multi-view geometry constraints) and deep learning (i.e. feature learning and basis depth maps learning) to address the challenging dense SfM problem. Experiments on large scale real data prove the success of the proposed method.

Renjiao Yi, Chenyang Zhu, Ping Tan et al.

We present a method for estimating detailed scene illumination using human faces in a single image. In contrast to previous works that estimate lighting in terms of low-order basis functions or distant point lights, our technique estimates illumination at a higher precision in the form of a non-parametric environment map. Based on the observation that faces can exhibit strong highlight reflections from a broad range of lighting directions, we propose a deep neural network for extracting highlights from faces, and then trace these reflections back to the scene to acquire the environment map. Since real training data for highlight extraction is very limited, we introduce an unsupervised scheme for finetuning the network on real images, based on the consistent diffuse chromaticity of a given face seen in multiple real images. In tracing the estimated highlights to the environment, we reduce the blurring effect of skin reflectance on reflected light through a deconvolution determined by prior knowledge on face material properties. Comparisons to previous techniques for highlight extraction and illumination estimation show the state-of-the-art performance of this approach on a variety of indoor and outdoor scenes.

Chengzhou Tang, Oliver Wang, Ping Tan

Many monocular visual SLAM algorithms are derived from incremental structure-from-motion (SfM) methods. This work proposes a novel monocular SLAM method which integrates recent advances made in global SfM. In particular, we present two main contributions to visual SLAM. First, we solve the visual odometry problem by a novel rank-1 matrix factorization technique which is more robust to the errors in map initialization. Second, we adopt a recent global SfM method for the pose-graph optimization, which leads to a multi-stage linear formulation and enables L1 optimization for better robustness to false loops. The combination of these two approaches generates more robust reconstruction and is significantly faster (4X) than recent state-of-the-art SLAM systems. We also present a new dataset recorded with ground truth camera motion in a Vicon motion capture room, and compare our method to prior systems on it and established benchmark datasets.

Rui Huang, Danping Zou, Richard Vaughan et al.

Image-based modeling techniques can now generate photo-realistic 3D models from images. But it is up to users to provide high quality images with good coverage and view overlap, which makes the data capturing process tedious and time consuming. We seek to automate data capturing for image-based modeling. The core of our system is an iterative linear method to solve the multi-view stereo (MVS) problem quickly and plan the Next-Best-View (NBV) effectively. Our fast MVS algorithm enables online model reconstruction and quality assessment to determine the NBVs on the fly. We test our system with a toy unmanned aerial vehicle (UAV) in simulated, indoor and outdoor experiments. Results show that our system improves the efficiency of data acquisition and ensures the completeness of the final model.

Zili Yi, Hao Zhang, Ping Tan et al.

Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a conditional GAN. However, human labeling is expensive, even impractical, and large quantities of data may not always be available. Inspired by dual learning from natural language translation, we develop a novel dual-GAN mechanism, which enables image translators to be trained from two sets of unlabeled images from two domains. In our architecture, the primal GAN learns to translate images from domain U to those in domain V, while the dual GAN learns to invert the task. The closed loop made by the primal and dual tasks allows images from either domain to be translated and then reconstructed. Hence a loss function that accounts for the reconstruction error of images can be used to train the translators. Experiments on multiple image translation tasks with unlabeled data show considerable performance gain of DualGAN over a single GAN. For some tasks, DualGAN can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data.

Xiaoming Deng, Shuo Yang, Yinda Zhang et al.

We propose a novel 3D neural network architecture for 3D hand pose estimation from a single depth image. Different from previous works that mostly run on 2D depth image domain and require intermediate or post process to bring in the supervision from 3D space, we convert the depth map to a 3D volumetric representation, and feed it into a 3D convolutional neural network(CNN) to directly produce the pose in 3D requiring no further process. Our system does not require the ground truth reference point for initialization, and our network architecture naturally integrates both local feature and global context in 3D space. To increase the coverage of the hand pose space of the training data, we render synthetic depth image by transferring hand pose from existing real image datasets. We evaluation our algorithm on two public benchmarks and achieve the state-of-the-art performance. The synthetic hand pose dataset will be available.

Xiaoming Deng, Ye Yuan, Yinda Zhang et al.

Hand detection is essential for many hand related tasks, e.g. parsing hand pose, understanding gesture, which are extremely useful for robotics and human-computer interaction. However, hand detection in uncontrolled environments is challenging due to the flexibility of wrist joint and cluttered background. We propose a deep learning based approach which detects hands and calibrates in-plane rotation under supervision at the same time. To guarantee the recall, we propose a context aware proposal generation algorithm which significantly outperforms the selective search. We then design a convolutional neural network(CNN) which handles object rotation explicitly to jointly solve the object detection and rotation estimation tasks. Experiments show that our method achieves better results than state-of-the-art detection models on widely-used benchmarks such as Oxford and Egohands database. We further show that rotation estimation and classification can mutually benefit each other.

Luwei Yang, Ligen Zhu, Yichen Wei et al.

Previous part-based attribute recognition approaches perform part detection and attribute recognition in separate steps. The parts are not optimized for attribute recognition and therefore could be sub-optimal. We present an end-to-end deep learning approach to overcome the limitation. It generates object parts from key points and perform attribute recognition accordingly, allowing adaptive spatial transform of the parts. Both key point estimation and attribute recognition are learnt jointly in a multi-task setting. Extensive experiments on two datasets verify the efficacy of proposed end-to-end approach.

Zhaopeng Cui, Nianjuan Jiang, Chengzhou Tang et al.

This paper derives a novel linear position constraint for cameras seeing a common scene point, which leads to a direct linear method for global camera translation estimation. Unlike previous solutions, this method deals with collinear camera motion and weak image association at the same time. The final linear formulation does not involve the coordinates of scene points, which makes it efficient even for large scale data. We solve the linear equation based on $L_1$ norm, which makes our system more robust to outliers in essential matrices and feature correspondences. We experiment this method on both sequentially captured images and unordered Internet images. The experiments demonstrate its strength in robustness, accuracy, and efficiency.