Lixin YANG (杨理欣)

Research Assistant Professor, 助理研究员,上海交通大学人工智能学院
Shanghai Jiao Tong University, School of Artificial Intelligence.
Member of Machine Vision and Intelligence Group (MVIG)
Email: siriusyang at sjtu dot edu dot cn

Bio.  I’m a Research Assistant Professor in Shanghai Jiao Tong University (SJTU), School of Artificial Intelligence (SAI). Since 2019, I have been part of the Machine Vision and Intelligence Group under the supervision of Prof. Cewu Lu, where I obtained my Ph.D. in 2023. Prior to that, I received my M.S degree at the Intelligent Robot Lab in SJTU.
My research interests include 3D Vision and Robotics. Currently, I am focusing on modeling and imitating the hand manipulating objects, including 3D hand | object pose | shape estimation, grasp | motion generation, imitation learning, dexterous manipulation.

Join Us.  I am looking for 1) Master Student at SJTU School of Artificial Intelligence, 2) self-motivated undergraduate research interns. Contact me if you are interested in the above topics

Email  /  Google Scholar  /  GitHub  /  Twitter

profile photo
News
  • [2024.09] 🎉 One paper on articulated object image manipulation got accepted by NeurIPS 2024 🇨🇦.
  • [2024.07] 🎉 One paper: SemGrasp is accepted by ECCV 2024 🇮🇹.
  • [2024.02] 🎉 One paper: OakInk2 is accepted by CVPR 2024 🇺🇸.
  • [2024.02] 🎉 The Contact Potential Field is accepted by TPAMI.
  • [2023.12] 🎉 One paper: FAVOR is accepted by AAAI 2024 🇨🇦.
  • [2023.10] 🎉 One paper: Color-NeuS is accepted by 3DV 2024 🇨🇭.
  • [2023.08] 📣 I defend my doctoral thesis and earn my Ph.D!
  • [2023.08] 👨🏻‍🏫 I am honored to be an invited speaker at the HANDS workshop at ICCV 2023.
  • [2023.07] 🎉 One paper: CHORD is accepted by ICCV 2023 🇫🇷.
  • [2023.06] 👨🏻‍🏫 Invited Talk at 智东西公开课 | 研讨会: 3D手部重建及具身智能交互. 视频 (中文).
  • [2023.02] 🎉 One paper: POEM is accepted by CVPR 2023.
  • [2022.10] 👩🏻‍❤️‍👨🏻 I have taken the wonderful journey of marriage alongside my cherished wife.
  • View older entries
    • [2022.10] 👨🏻‍🏫 Invited Talk at International Digital Economy Academy (IDEA), Thanks Ailing Zeng for hosting.
    • [2022.09] 🎉 One paper: DART got accepted by NeurIPS 2022 - Datasets and Benchmarks Track.
    • [2022.07] 👨🏻‍🏫 Invited Talk at 智东西公开课 | AI新青年讲座: 基于图像的手物交互重建与虚拟人手生成. 视频 (中文).
    • [2022.04] 👨🏻‍🏫 Invited Talk at MPI-IS Perceiving Systems. Thanks Yuliang Xiu for hosting. (info).
    • [2022.03] 🎉 Two paper were accepted by CVPR 2022: one Oral, one poster.
    • [2021.07] 🎉 One paper got accepted by ICCV 2021.
Publications
Motion Before Action: Diffusing Object Motion as Manipulation Condition
Yue Su*,  Xinyu Zhan*,  Hongjie FangYong-Lu LiCewu LuLixin Yang#, 

arXiv preprint, 2024
project / arXiv / code

A two cascaded diffusion processes for object motion generation and robot action generation under object motion guidance.

SemGrasp: Semantic Grasp Generation via Language Aligned Discretization
Kailin LiJingbo WangLixin YangCewu LuBo Dai

ECCV, 2024
project / arXiv

A MLLM-based method that infuses language instructions into grasp generation; & A new language-pose dataset, CapGrasp, featuring detailed caption of grasping poses.

OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion
Xinyu Zhan* ,  Lixin Yang* ,  Yifei Zhao,  Kangrui Mao,  Hanlin Xu,  Zenan Lin,  Kailin LiCewu Lu

CVPR, 2024
project / arXiv

A 4D motion dataset focusing on bimanual object manipulation tasks involved in complex daily activities; & A three-tiered task abstraction: Object Affordance, Primitive Task, and Complex Task, to systematically organize manipulation tasks.

FAVOR: Full-Body AR-Driven Virtual Object Rearrangement Guided by Instruction Text
Kailin Li* ,  Lixin Yang* ,  Zenan Lin,  Jian Xu,  Xinyu Zhan,  Yifei Zhao,  Pengxiang Zhu,  Wenxiong Kang,  Kejian Wu,  Cewu Lu

AAAI, 2024
(coming): project / arXiv / code / data

A full-body human motion dataset that captures text-guided desktop object rearrangement through MoCap and AR glasses; & A pipeline for generating avatar's motion of object rearrangement driven by text instruction.

Color-NeuS: Reconstructing Neural Implicit Surfaces with Color
Licheng Zhong* ,  Lixin Yang* ,  Kailin LiHaoyu ZhenMei HanCewu Lu

3DV, 2024
project / arXiv / code / data

A NeuS-based reconstruction method for both object surface and texture. Can be used to reconstruct object with complex geometry and texture given a hand-held object video.

CHORD: Category-level in-Hand Object Reconstruction via Shape Deformation
Kailin Li * ,  Lixin Yang* ,  Haoyu ZhenZenan LinXinyu ZhanLicheng ZhongJian XuKejian WuCewu Lu

ICCV, 2023
project / arXiv / code (coming) / tool

A single-view hand-held object reconstruction method that exploits the categorical shape prior to reconstruct the shape of intra-class objects; & A new synthetic dataset, COMIC, that contains the category-level collection of objects with diverse shape, materials, interacting poses, and viewing directions.

POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo
Lixin YangJian XuLicheng ZhongXinyu ZhanZhicheng Wang
Kejian WuCewu Lu

CVPR, 2023
arXiv / code

A multi-view hand mesh recovery (HMR) method with Transformer. It leverages the "power of points", including Basis Points Set, point's positional encoding and point-Transformer, to unify and merge information from sparsely arranged cameras.

DART: Articulated Hand Model with Diverse Accessories and Rich Textures
Daiheng Gao*,   Yuliang Xiu*,  Kailin Li*,  Lixin Yang*,
Feng Wang, Peng Zhang, Bang Zhang, Cewu Lu, Ping Tan

NeurIPS, 2022 - Datasets and Benchmarks Track
project / arXiv / code / video

A MANO-derived hand model that contains 325 exquisite hand-crafted texture maps (vary in appearance and cover different kinds of blemishes, make-ups, and accessories).

OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction
Lixin Yang*, Kailin Li* Xinyu Zhan*, Fei Wu, Anran Xu, Liu Liu, Cewu Lu
(*=equal contribution)

CVPR, 2022
project / paper / arXiv / code

A dataset that focuses on human grasp based on object's affordance. It contains two knowledge base: 1) Object affordance knowledge (Oak) and 2) Interaction knowledge (Ink).
A new model: Tink, for transferring interaction pose from one object to another.

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, Cewu Lu
(*=equal contribution)

CVPR, 2022   (Oral Presentation)
paper / arXiv / code

An online data syhthesis tool for articulated hand(-object) pose estimation. An grasping systhesis method that can generate dexterous hand grasping poses for arbitrary object.

CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction
Lixin Yang, Xinyu Zhan, Kailin Li, Wenqiang Xu, Jiefeng Li, Cewu Lu

ICCV, 2021
project / paper / supp / arXiv / code / 知乎

A novel contact representation (CPF) that used to imporve physical hand-object interaction. A hybrid learning-fitting framework (MIHO) that aligns the top-down pose estimation with bottom-up contact modeling.

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
Jiefeng Li, Chao Xu, Zhicun Chen, Siyuan Bian, Lixin Yang, Cewu Lu

CVPR, 2021
project / paper / supp / arXiv / code
HandTailor: Towards High-Precision Monocular 3D Hand Recovery
Jun Lv, Wenqiang Xu, Lixin Yang, Sucheng Qian, Chongzhao Mao, Cewu Lu

BMVC, 2021
paper / arXiv / code
BiHand: Recovering Hand Mesh with Multi-stage Bisected Hourglass Networks
Lixin Yang, Jiasen Li, Wenqiang Xu, Yiqun Diao, Cewu Lu

BMVC, 2020
paper / arXiv / code


website template