publications

Human is the measure of all things. Thus, to achieve truly general intelligence, we should strive to create a system that can think and act comparably to humans. Admittedly, for many tasks, we don't need a system as sophisticated as a human being. We also don't need to fully comprehend the mechanisms of human intelligence to develop a system with remarkable generalization capabilities. However, these system are still not generalist agent, no matter what the PR says.
My research interest starts from general object understanding, and has recently shifted to human-centric manipulation. Many onging projects in new areas do not reflect in the paper list yet.

* indicates equal contribution. publications by categories in reversed chronological order.

2024

  1. vitam.png
    Capturing forceful interaction with deformable objects using a deep learning-powered stretchable tactile array
    Chunpeng Jiang*, Wenqiang Xu*, Yutong Li, Zhenjun Yu, Longchun Wang, Xiaotong Hu, Zhengyi Xie, Qingkun Liu, Bin Yang, Xiaolin Wang, Wenxin Du, Tutian Tang, Dongzhe Zheng, Siqiong Yao, Cewu Lu, and Jingquan Liu
    Nature Communications, 2024
  2. zema.png
    Intersection-free Robot Manipulation with Soft-Rigid Coupled Incremental Potential Contact
    Wenxin Du*, Siqiong Yao*, Xinlei Wang, Yuhang Xu, Wenqiang Xu, and Cewu Lu
    IEEE Robotics and Automation Letters, 2024
  3. cpf.png
    Learning a Contact Potential Field for Modeling the Hand-Object Interaction
    Lixin Yang*, Xinyu Zhan*, Kailin Li, Wenqiang Xu, Junming Zhang, Jiefeng Li, and Cewu Lu
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
  4. msmano.png
    MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints
    Pengfei Xie*, Wenqiang Xu*, Tutian Tang, Zhenjun Yu, and Cewu Lu
    In CVPR IEEE Conference on Computer Vision and Pattern Recognition, 2024
  5. tacipc.png
    TacIPC: Intersection- and Inversion-free FEM-based Elastomer Simulation For Optical Tactile Sensors
    Wenxin Du*, Wenqiang Xu*, Jieji Ren, Zhenjun Yu, and Cewu Lu
    IEEE Robotics and Automation Letters, 2024
  6. diffcp.png
    Differentiable Cloth Parameter Identification and State Estimation in Manipulation
    Dongzhe Zheng*, Siqiong Yao*, Wenqiang Xu, and Cewu Lu
    IEEE Robotics and Automation Letters, 2024
  7. rftrans.png
    RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation
    Tutian Tang*, Jiyu Liu*, Jieyi Zhang, Haoyuan Fu, Wenqiang Xu, and Cewu Lu
    IEEE Robotics and Automation Letters, 2024
  8. dipgrasp.jpg
    DiPGrasp: Parallel Local Searching for Efficient Differentiable Grasp Planning
    Wenqiang Xu*, Jieyi Zhang*, Tutian Tang, Zhenjun Yu, Yutong Li, and Cewu Lu
    IEEE Robotics and Automation Letters, 2024
  9. diffstir.gif
    Differentiable Fluid Physics Parameter Identification By Stirring and For Stirring
    Wenqiang Xu*, Dongzhe Zheng*, Yutong Li, Jieji Ren, and Cewu Lu
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024 Oral Pitch

2023

  1. tnt.gif
    Precise Robotic Needle-Threading with Tactile Perception and Reinforcement Learning
    Zhenjun Yu*, Wenqiang Xu*, Siqiong Yao, Jieji Ren, Tutian Tang, Yutong Li, Guoying Gu, and Cewu Lu
    In CoRL Conference on Robot Learning, 2023
  2. unifolding.gif
    UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding
    Han Xue*, Yutong Li*, Wenqiang Xu, Huanyu Li, Dongzhe Zheng, and Cewu Lu
    In CoRL Conference on Robot Learning, 2023
  3. clothpose.png
    ClothPose: A Real-World Benchmark for Visual Analysis of Garment Pose via An Indirect Recording Solution
    Wenqiang Xu*, Wenxin Du*, Han Xue, Yutong Li, Ruolin Ye, Yan-Feng Wang, and Cewu Lu
    In ICCV IEEE/CVF International Conference on Computer Vision, 2023 Oral
  4. rfu.gif
    Demonstrating RFUniverse: A Multiphysics Simulation Platform for Embodied AI
    Haoyuan Fu*, Wenqiang Xu*, Ruolin Ye*, Han Xue, Zhenjun Yu, Tutian Tang, Yutong Li, Wenxin Du, Jieyi Zhang, and Cewu Lu
    In RSS Robotics: Science and Systems, 2023
  5. vtaco.png
    Visual-Tactile Sensing for In-Hand Object Reconstruction
    Wenqiang Xu*, Zhenjun Yu*, Han Xue, Ruolin Ye, Siqiong Yao, and Cewu Lu
    In CVPR IEEE Conference on Computer Vision and Pattern Recognition, 2023
  6. garmenttracking.gif
    GarmentTracking: Category-Level Garment Pose Tracking
    Han Xue, Wenqiang Xu, Jieyi Zhang, Tutian Tang, Yutong Li, Wenxin Du, Ruolin Ye, and Cewu Lu
    In CVPR IEEE Conference on Computer Vision and Pattern Recognition, 2023
  7. bidirection.jpg
    Bidirectional Visual-Tactile Cross-Modal Generation Using Latent Feature Space Flow Model
    Yu Fang, Xuehe Zhang, Wenqiang Xu, Gangfeng Liu, and Jie Zhao
    Neural Networks, 2023

2022

  1. rcare.gif
    RCare World: A Human-centric Simulation World for Caregiving Robots
    Ruolin Ye*, Wenqiang Xu*, Haoyuan Fu, Rajat Kumar Jenamani, Vy Nguyen, Cewu Lu, Katherine Dimitropoulou, and Tapomayukh Bhattacharjee
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022 Best RoboCup Award & Best Paper Finalist
  2. akb48.png
    AKB-48: A Real-World Articulated Object Knowledge Base
    Liu Liu, Wenqiang Xu, Haoyuan Fu, Sucheng Qian, Qiaojun Yu, Yang Han, and Cewu Lu
    In CVPR IEEE Conference on Computer Vision and Pattern Recognition, 2022
  3. robotube.png
    RoboTube: Learning Household Manipulation from Human Videos with Simulated Twin Environments
    Haoyu Xiong*, Haoyuan Fu*, Jieyi Zhang, Chen Bao, Qiang Zhang, Yongxi Huang, Wenqiang Xu, Animesh Garg, and Cewu Lu
    In CoRL Conference on Robot Learning, 2022 Oral
  4. artiboost.png
    ArtiBoost: Boosting Articulated 3d Hand-object Pose Estimation via Online Exploration and Synthesis
    Lixin Yang*, Kailin Li*, Xinyu Zhan, Jun Lv, Wenqiang Xu, Jiefeng Li, and Cewu Lu
    In CVPR IEEE Conference on Computer Vision and Pattern Recognition, 2022 Oral
  5. sagci.png
    SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning
    Jun Lv*, Qiaojun Yu*, Lin Shao*, Wenhai Liu, Wenqiang Xu, and Cewu Lu
    In IEEE International Conference on Robotics and Automation, 2022
  6. reart48.png
    Toward Real-World Category-Level Articulation Pose Estimation
    Liu Liu, Han Xue, Wenqiang Xu, Haoyuan Fu, and Cewu Lu
    IEEE Transactions on Image Processing, 2022

2021

  1. omad.png
    OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrieval
    Han Xue*, Liu Liu*, Wenqiang Xu, Haoyuan Fu, and Cewu Lu
    In BMVC British Machine Vision Conference, 2021
  2. handtailor.png
    HandTailor: Towards High-Precision Monocular 3D Hand Recovery
    Jun Lv, Wenqiang Xu, Lixin Yang, Sucheng Qian, Chongzhao Mao, and Cewu Lu
    In BMVC British Machine Vision Conference, 2021
  3. cpf.png
    CPF: Learning a Contact Potential Field to Model the Hand-object Interaction
    Lixin Yang*, Xinyu Zhan*, Kailin Li, Wenqiang Xu, Jiefeng Li, and Cewu Lu
    In ICCV IEEE/CVF International Conference on Computer Vision, 2021
  4. h2o.png
    H2O: A Benchmark for Visual Human-human Object Handover Analysis
    Ruolin Ye*, Wenqiang Xu*, Zhendong Xue, Tutian Tang, Yanfeng Wang, and Cewu Lu
    In ICCV IEEE/CVF International Conference on Computer Vision, 2021

2020

  1. bihand.png
    BiHand: Recovering Hand Mesh with Multi-stage Bisected Hourglass Networks
    Lixin Yang, Jiasen Li, Wenqiang Xu, Yiqun Diao, and Cewu Lu
    In BMVC British Machine Vision Conference, 2020

2019

  1. eseseg.png
    Explicit Shape Encoding for Real-time Instance Segmentation
    Wenqiang Xu*, Haiyang Wang*, Fubo Qi, and Cewu Lu
    In ICCV IEEE/CVF International Conference on Computer Vision, 2019

2018

  1. srda.png
    SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation
    Wenqiang Xu*, Yonglu Li*, and Cewu Lu
    In ECCV European Conference on Computer Vision, 2018