Author name cluster

Wenbing Tao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

19 papers

2 author rows

TMLR Journal 2025 Journal Article

Adaptive Multi-step Refinement Network for Robust Point Cloud Registration

Zhi Chen
Yufan Ren
Tong Zhang
Zheng Dang
Wenbing Tao
Sabine Susstrunk
Mathieu Salzmann

Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds of the same scene. Despite significant progress with learning-based approaches, existing methods still face challenges when the overlapping region between the two point clouds is small. In this paper, we propose an adaptive multi-step refinement network that refines the registration quality at each step by leveraging the information from the preceding step. To achieve this, we introduce a training procedure and a refinement network. Firstly, to adapt the network to the current step, we utilize a generalized one-way attention mechanism, which prioritizes the last step's estimated overlapping region, and we condition the network on step indices. Secondly, instead of training the network to map either random transformations or a fixed pre-trained model's estimations to the ground truth, we train it on transformations with varying registration qualities, ranging from accurate to inaccurate, thereby enhancing the network's adaptiveness and robustness. Despite its conceptual simplicity, our method achieves state-of-the-art performance on both the 3DMatch/3DLoMatch and KITTI benchmarks. Notably, on 3DLoMatch, our method reaches 80.4% recall rate, with an absolute improvement of 1.2%.

PDF Details

AAAI Conference 2025 Conference Paper

Cross-View Referring Multi-Object Tracking

Sijia Chen
En Yu
Wenbing Tao

Referring Multi-Object Tracking (RMOT) is an important topic in the current tracking field. Its task form is to guide the tracker to track objects that match the language description. Current research mainly focuses on referring multi-object tracking under single-view, which refers to a view sequence or multiple unrelated view sequences. However, in the single-view, some appearances of objects are easily invisible, resulting in incorrect matching of objects with the language description. In this work, we propose a new task, called Cross-view Referring Multi-Object Tracking (CRMOT). It introduces the cross-view to obtain the appearances of objects from multiple views, avoiding the problem of the invisible appearances of objects in RMOT task. CRMOT is a more challenging task of accurately tracking the objects that match the language description and maintaining the identity consistency of objects in each cross-view. To advance CRMOT task, we construct a cross-view referring multi-object tracking benchmark based on CAMPUS and DIVOTrack datasets, named CRTrack. Specifically, it provides 13 different scenes and 221 language descriptions. Furthermore, we propose an end-to-end cross-view referring multi-object tracking method, named CRTracker. Extensive experiments on the CRTrack benchmark verify the effectiveness of our method.

PDF Details DOI

IROS Conference 2025 Conference Paper

FIELD: Fast Information-driven Autonomous Exploration using Larger Perception Distance

Yuefeng Zhang
Fan Yang 0088
Nanjun Yuan
Wenbing Tao

Autonomous exploration is a critical challenge for various unmanned aerial vehicle (UAV) applications. Existing methods often suffer from low exploration rates due to limitations such as inefficient global coverage and inadequate sensor data utilization. In this paper, we introduce FIELD, a Fast Information-driven aerial robot Exploration planner using Larger perception Distance. FIELD leverages a larger perception distance to identify high-information-gain viewpoints while maintaining mapping precision and utilizing more sensor data to guide the exploration process. Then, the method incorporates a history-aware coverage path to determine a consistent and reasonable sequence for visiting frontier viewpoints. Local viewpoints are refined to find the optimal combination of these viewpoints. We compare our method with state-of-the-art frontier-based approaches in benchmark environments. Our method significantly improves exploration efficiency by 13% to 17%.

Details

ICLR Conference 2025 Conference Paper

OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer

Jinyang Li
En Yu
Sijia Chen
Wenbing Tao

Open-vocabulary multiple object tracking aims to generalize trackers to unseen categories during training, enabling their application across a variety of real-world scenarios. However, the existing open-vocabulary tracker is constrained by its framework structure, isolated frame-level perception, and insufficient modal interactions, which hinder its performance in open-vocabulary classification and tracking. In this paper, we propose OVTR (End-to-End Open-Vocabulary Multiple Object Tracking with TRansformer), the first end-to-end open-vocabulary tracker that models motion, appearance, and category simultaneously. To achieve stable classification and continuous tracking, we design the CIP (Category Information Propagation) strategy, which establishes multiple high-level category information priors for subsequent frames. Additionally, we introduce a dual-branch structure for generalization capability and deep multimodal interaction, and incorporate protective strategies in the decoder to enhance performance. Experimental results show that our method surpasses previous trackers on the open-vocabulary MOT benchmark while also achieving faster inference speeds and significantly reducing preprocessing requirements. Moreover, the experiment transferring the model to another dataset demonstrates its strong adaptability.

Details

NeurIPS Conference 2025 Conference Paper

Perception-R1: Pioneering Perception Policy with Reinforcement Learning

En Yu
Kangheng Lin
Liang Zhao
jisheng yin
Yana Wei
Yuang Peng
Haoran Wei
Jianjian Sun

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking process through RL does not consistently lead to performance gains across all visual perception tasks. This leads us to delve into the essential role of RL in the context of visual perception. In this work, we return to the fundamentals and explore the effects of RL on different perception tasks. We observe that the perceptual perplexity is a major factor in determining the effectiveness of RL. We also observe that reward design plays a crucial role in further approaching the upper limit of model perception. To leverage these findings, we propose Perception-R1, a scalable RL framework using GRPO during MLLM post-training. With a standard Qwen2-VL-2B-Instruct, Perception-R1 achieves +4. 2% on RefCOCO+, +17. 9% on PixMo-Count, +4. 2% on PageOCR, and notably, 31. 9% AP on COCO2017 val for the first time, establishing a strong baseline for perception policy learning.

PDF Details

ICLR Conference 2025 Conference Paper

Unhackable Temporal Reward for Scalable Video MLLMs

En Yu
Kangheng Lin
Liang Zhao
Yana Wei
Zining Zhu 0004
Haoran Wei
Jianjian Sun
Zheng Ge

In the pursuit of superior video-processing MLLMs, we have encountered a perplexing paradox: the “anti-scaling law”, where more data and larger models lead to worse performance. This study unmasks the culprit: “temporal hacking”, a phenomenon where models shortcut by fixating on select frames, missing the full video narrative. In this work, we systematically establish a comprehensive theory of temporal hacking, defining it from a reinforcement learning perspective, introducing the Temporal Perplexity (TPL) score to assess this misalignment, and proposing the Unhackable Temporal Rewarding (UTR) framework to mitigate the temporal hacking. Both theoretically and empirically, TPL proves to be a reliable indicator of temporal modeling quality, correlating strongly with frame activation patterns. Extensive experiments reveal that UTR not only counters temporal hacking but significantly elevates video comprehension capabilities. This work not only advances video-AI systems but also illuminates the critical importance of aligning proxy rewards with true objectives in MLLM development.

Details

IJCAI Conference 2024 Conference Paper

A Comprehensive Survey and Taxonomy on Point Cloud Registration Based on Deep Learning

Yu-Xin Zhang
Jie Gui
Xiaofeng Cong
Xin Gong
Wenbing Tao

Point cloud registration (PCR) involves determining a rigid transformation that aligns one point cloud to another. Despite the plethora of outstanding deep learning (DL)-based registration methods proposed, comprehensive and systematic studies on DL-based PCR techniques are still lacking. In this paper, we present a comprehensive survey and taxonomy of recently proposed PCR methods. Firstly, we conduct a taxonomy of commonly utilized datasets and evaluation metrics. Secondly, we classify the existing research into two main categories: supervised and unsupervised registration, providing insights into the core concepts of various influential PCR models. Finally, we highlight open challenges and potential directions for future research. A curated collection of valuable resources is made available at https: //github. com/yxzhang15/PCR.

PDF Details DOI

AAAI Conference 2024 Conference Paper

IINet: Implicit Intra-inter Information Fusion for Real-Time Stereo Matching

Ximeng Li
Chen Zhang
Wanjuan Su
Wenbing Tao

Recently, there has been a growing interest in 3D CNN-based stereo matching methods due to their remarkable accuracy. However, the high complexity of 3D convolution makes it challenging to strike a balance between accuracy and speed. Notably, explicit 3D volumes contain considerable redundancy. In this study, we delve into more compact 2D implicit network to eliminate redundancy and boost real-time performance. However, simply replacing explicit 3D networks with 2D implicit networks causes issues that can lead to performance degradation, including the loss of structural information, the quality decline of inter-image information, as well as the inaccurate regression caused by low-level features. To address these issues, we first integrate intra-image information to fuse with inter-image information, facilitating propagation guided by structural cues. Subsequently, we introduce the Fast Multi-scale Score Volume (FMSV) and Confidence Based Filtering (CBF) to efficiently acquire accurate multi-scale, noise-free inter-image information. Furthermore, combined with the Residual Context-aware Upsampler (RCU), our Intra-Inter Fusing network is meticulously designed to enhance information transmission on both feature-level and disparity-level, thereby enabling accurate and robust regression. Experimental results affirm the superiority of our network in terms of both speed and accuracy compared to all other fast methods.

PDF Details DOI

IROS Conference 2024 Conference Paper

QTrack: Embracing Quality Clues for Robust 3D Multi-Object Tracking

Jinrong Yang
En Yu
Zeming Li
Xiaoping Li 0005
Wenbing Tao

3D Multi-Object Tracking (MOT) has achieved tremendous achievement thanks to the rapid development of 3D object detection and 2D MOT. Recent advanced works generally employ a series of object attributes, e. g. , position, size, velocity, and appearance, to provide the clues for the association in 3D MOT. However, these cues may not be reliable due to some visual noise, such as occlusion and blur, leading to tracking performance bottlenecks. To reveal the dilemma, we conduct extensive empirical analysis to expose the key bottleneck of each clue and how they correlate with each other. The analysis results motivate us to efficiently absorb the merits among all cues and adaptively produce an optimal tracking manner. Specifically, we present Location and Velocity Quality Learning, which efficiently guides the network to estimate the quality of predicted object attributes. Based on these quality estimations, we propose a quality-aware object association (QOA) strategy to leverage the quality score as an important reference factor for achieving robust association. Despite its simplicity, extensive experiments indicate that the proposed strategy significantly boosts tracking performance by 2. 2% AMOTA and our method outperforms all existing state-of-the-art works on nuScenes by a large margin. Moreover, QTrack achieves 51. 1%, 54. 8% and 56. 6% AMOTA tracking performance on the nuScenes test sets with BEVDepth, VideoBEV, and StreamPETR models respectively, which significantly reduces the performance gap between the pure camera and LiDAR-based trackers.

Details

AAAI Conference 2023 Conference Paper

Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation

Wanjuan Su
Wenbing Tao

Over the years, learning-based multi-view stereo methods have achieved great success based on their coarse-to-fine depth estimation frameworks. However, 3D CNN-based cost volume regularization inevitably leads to over-smoothing problems at object boundaries due to its smooth properties. Moreover, discrete and sparse depth hypothesis sampling exacerbates the difficulty in recovering the depth of thin structures and object boundaries. To this end, we present an Efficient edge-Preserving multi-view stereo Network (EPNet) for practical depth estimation. To keep delicate estimation at details, a Hierarchical Edge-Preserving Residual learning (HEPR) module is proposed to progressively rectify the upsampling errors and help refine multi-scale depth estimation. After that, a Cross-view Photometric Consistency (CPC) is proposed to enhance the gradient flow for detailed structures, which further boosts the estimation accuracy. Last, we design a lightweight cascade framework and inject the above two strategies into it to achieve better efficiency and performance trade-offs. Extensive experiments show that our method achieves state-of-the-art performance with fast inference speed and low memory usage. Notably, our method tops the first place on challenging Tanks and Temples advanced dataset and ETH3D high-res benchmark among all published learning-based methods. Code will be available at https://github.com/susuwj/EPNet.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation

En Yu
Songtao Liu
Zhuoling Li
Jinrong Yang
Zeming Li
Shoudong Han
Wenbing Tao

Although existing multi-object tracking (MOT) algorithms have obtained competitive performance on various benchmarks, almost all of them train and validate models on the same domain. The domain generalization problem of MOT is hardly studied. To bridge this gap, we first draw the observation that the high-level information contained in natural language is domain invariant to different tracking domains. Based on this observation, we propose to introduce natural language representation into visual MOT models for boosting the domain generalization ability. However, it is infeasible to label every tracking target with a textual description. To tackle this problem, we design two modules, namely visual context prompting (VCP) and visual-language mixing (VLM). Specifically, VCP generates visual prompts based on the input frames. VLM joints the information in the generated visual prompts and the textual prompts from a pre-defined Trackbook to obtain instance-level pseudo textual description, which is domain invariant to different tracking scenes. Through training models on MOT17 and validating them on MOT20, we observe that the pseudo textual descriptions generated by our proposed modules improve the generalization performance of query-based trackers by large margins.

PDF Details DOI

AAAI Conference 2022 Conference Paper

DeTarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration

Zhi Chen
Fan Yang
Wenbing Tao

Point cloud registration is a fundamental step for many tasks. In this paper, we propose a neural network named DetarNet to decouple the translation t and rotation R, so as to overcome the performance degradation due to their mutual interference in point cloud registration. First, a Siamese Network based Progressive and Coherent Feature Drift (PCFD) module is proposed to align the source and target points in highdimensional feature space, and accurately recover translation from the alignment process. Then we propose a Consensus Encoding Unit (CEU) to construct more distinguishable features for a set of putative correspondences. After that, a Spatial and Channel Attention (SCA) block is adopted to build a classification network for finding good correspondences. Finally, the rotation is obtained by Singular Value Decomposition (SVD). In this way, the proposed network decouples the estimation of translation and rotation, resulting in better performance for both of them. Experimental results demonstrate that the proposed DetarNet improves registration performance on both indoor and outdoor scenes. Our code will be available in https: //github. com/ZhiChen902/DetarNet.

PDF Details

NeurIPS Conference 2022 Conference Paper

Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction

Qiancheng Fu
Qingshan Xu
Yew Soon Ong
Wenbing Tao

Recently, neural implicit surfaces learning by volume rendering has become popular for multi-view reconstruction. However, one key challenge remains: existing approaches lack explicit multi-view geometry constraints, hence usually fail to generate geometry-consistent surface reconstruction. To address this challenge, we propose geometry-consistent neural implicit surfaces learning for multi-view reconstruction. We theoretically analyze that there exists a gap between the volume rendering integral and point-based signed distance function (SDF) modeling. To bridge this gap, we directly locate the zero-level set of SDF networks and explicitly perform multi-view geometry optimization by leveraging the sparse geometry from structure from motion (SFM) and photometric consistency in multi-view stereo. This makes our SDF optimization unbiased and allows the multi-view geometry constraints to focus on the true surface optimization. Extensive experiments show that our proposed method achieves high-quality surface reconstruction in both complex thin structures and large smooth regions, thus outperforming the state-of-the-arts by a large margin.

PDF Details

NeurIPS Conference 2022 Conference Paper

One-Inlier is First: Towards Efficient Position Encoding for Point Cloud Registration

Fan Yang
Lin Guo
Zhi Chen
Wenbing Tao

Transformer architecture has shown great potential for many visual tasks, including point cloud registration. As an order-aware module, position encoding plays an important role in Transformer architecture applied to point cloud registration task. In this paper, we propose OIF-PCR, a one-inlier based position encoding method for point cloud registration network. Specifically, we first find one correspondence by a differentiable optimal transport layer, and use it to normalize each point for position encoding. It can eliminate the challenges brought by the different reference frames of two point clouds, and mitigate the feature ambiguity by learning the spatial consistency. Then, we propose a joint approach for establishing correspondence and position encoding, presenting an iterative optimization process. Finally, we design a progressive way for point cloud alignment and feature learning to gradually optimize the rigid transformation. The proposed position encoding is very efficient, requiring only a small addition of memory and computing overhead. Extensive experiments demonstrate the proposed method can achieve competitive performance with the state-of-the-art methods in both indoor and outdoor scenes.

PDF Details

AAAI Conference 2021 Conference Paper

Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences

Zhi Chen
Fan Yang
Wenbing Tao

Finding good correspondences is a critical prerequisite in many feature based tasks. Given a putative correspondence set of an image pair, we propose a neural network which finds correct correspondences by a binary-class classifier and estimates relative pose through classified correspondences. First, we analyze that due to the imbalance in the number of correct and wrong correspondences, the loss function has a great impact on the classification results. Thus, we propose a new Guided Loss that can directly use evaluation criterion (Fn-measure) as guidance to dynamically adjust the objective function during training. We theoretically prove that the perfect negative correlation between the Guided Loss and Fnmeasure, so that the network is always trained towards the direction of increasing Fn-measure to maximize it. We then propose a hybrid attention block to extract feature, which integrates the Bayesian attentive context normalization (BACN) and channel-wise attention (CA). BACN can mine the prior information to better exploit global context and CA can capture complex channel context to enhance the channel awareness of the network. Finally, based on our Guided Loss and hybrid attention block, a cascade network is designed to gradually optimize the result for more superior performance. Experiments have shown that our network achieves the state-ofthe-art performance on benchmark datasets. Our code will be available in https: //github. com/wenbingtao/GLHA.

PDF Details

AAAI Conference 2021 Conference Paper

DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction

Yiming Luo
Zhenxing Mi
Wenbing Tao

In this paper, a novel learning-based network, named DeepDT, is proposed to reconstruct the surface from Delaunay triangulation of point cloud. DeepDT learns to predict inside/outside labels of Delaunay tetrahedrons directly from a point cloud and corresponding Delaunay triangulation. The local geometry features are first extracted from the input point cloud and aggregated into a graph deriving from the Delaunay triangulation. Then a graph filtering is applied on the aggregated features in order to add structural regularization to the label prediction of tetrahedrons. Due to the complicated spatial relations between tetrahedrons and the triangles, it is impossible to directly generate ground truth labels of tetrahedrons from ground truth surface. Therefore, we propose a multi-label supervision strategy which votes for the label of a tetrahedron with labels of sampling locations inside it. The proposed DeepDT can maintain abundant geometry details without generating overly complex surfaces, especially for inner surfaces of open scenes. Meanwhile, the generalization ability and time consumption of the proposed method is acceptable and competitive compared with the state-of-the-art methods. Experiments demonstrate the superior performance of the proposed DeepDT.

PDF Details

AAAI Conference 2020 Conference Paper

JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds

Lin Zhao
Wenbing Tao

In this paper, we propose a novel joint instance and semantic segmentation approach, which is called JSNet, in order to address the instance and semantic segmentation of 3D point clouds simultaneously. Firstly, we build an effective backbone network to extract robust features from the raw point clouds. Secondly, to obtain more discriminative features, a point cloud feature fusion module is proposed to fuse the different layer features of the backbone network. Furthermore, a joint instance semantic segmentation module is developed to transform semantic features into instance embedding space, and then the transformed features are further fused with instance features to facilitate instance segmentation. Meanwhile, this module also aggregates instance features into semantic feature space to promote semantic segmentation. Finally, the instance predictions are generated by applying a simple mean-shift clustering on instance embeddings. As a result, we evaluate the proposed JSNet on a large-scale 3D indoor point cloud dataset S3DIS and a part dataset ShapeNet, and compare it with existing approaches. Experimental results demonstrate our approach outperforms the state-of-theart method in 3D instance segmentation with a signiﬁcant improvement in 3D semantic prediction and our method is also beneﬁcial for part segmentation. The source code for this work is available at https: //github. com/dlinzhao/JSNet.

PDF Details

AAAI Conference 2020 Conference Paper

Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume

Qingshan Xu
Wenbing Tao

Deep learning has shown to be effective for depth inference in multi-view stereo (MVS). However, the scalability and accuracy still remain an open problem in this domain. This can be attributed to the memory-consuming cost volume representation and inappropriate depth inference. Inspired by the group-wise correlation in stereo matching, we propose an average group-wise correlation similarity measure to construct a lightweight cost volume. This can not only reduce the memory consumption but also reduce the computational burden in the cost volume ﬁltering. Based on our effective cost volume representation, we propose a cascade 3D U-Net module to regularize the cost volume to further boost the performance. Unlike the previous methods that treat multi-view depth inference as a depth regression problem or an inverse depth classiﬁcation problem, we recast multi-view depth inference as an inverse depth regression task. This allows our network to achieve sub-pixel estimation and be applicable to largescale scenes. Through extensive experiments on DTU dataset and Tanks and Temples dataset, we show that our proposed network with Correlation cost volume and Inverse DEpth Regression (CIDER1 ), achieves state-of-the-art results, demonstrating its superior performance on scalability and accuracy.

PDF Details

AAAI Conference 2020 Conference Paper

Planar Prior Assisted PatchMatch Multi-View Stereo

Qingshan Xu
Wenbing Tao

The completeness of 3D models is still a challenging problem in multi-view stereo (MVS) due to the unreliable photometric consistency in low-textured areas. Since low-textured areas usually exhibit strong planarity, planar models are advantageous to the depth estimation of low-textured areas. On the other hand, PatchMatch multi-view stereo is very efﬁcient for its sampling and propagation scheme. By taking advantage of planar models and PatchMatch multi-view stereo, we propose a planar prior assisted PatchMatch multi-view stereo framework in this paper. In detail, we utilize a probabilistic graphical model to embed planar models into PatchMatch multi-view stereo and contribute a novel multi-view aggregated matching cost. This novel cost takes both photometric consistency and planar compatibility into consideration, making it suited for the depth estimation of both non-planar and planar regions. Experimental results demonstrate that our method can efﬁciently recover the depth information of extremely low-textured areas, thus obtaining high complete 3D models and achieving state-of-the-art performance.

PDF Details