|
ICRA, 2026 project / arXiv A cross-embodiment framework that transfers wheeled-humanoid data to bipedal VLA models via morphology-agnostic 6D end-effector trajectories and a heuristic-enhanced online DAgger controller. |
|||||||||
|
TPAMI, 2025 paper / arXiv / code POEM-v2: a generalizable multi-view 3D hand reconstruction model trained on large-scale multi-view datasets. It enables accurate, flexible, and occlusion-robust hand mesh recovery across arbitrary multi-view setups. |
|||||||||
|
CoRL, 2025 (Oral Presentation) project / arXiv AirExo-2, a low-cost exoskeleton system for large-scale in-the-wild demonstration collection. It transforms the collected in-the-wild demonstrations into pseudo-robot demonstrations. RISE-2, a generalizable imitation policy that integrates 2D and 3D perceptions. |
|||||||||
|
ICCV, 2025 project / arXiv a bidirectionally expanded learning approach that enhances auto-regressive policies for robotic manipulation. It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner with logarithmic-time inference. |
|||||||||
|
RA-L, 2025 & ICRA, 2026 project / arXiv / code A two cascaded diffusion processes for object motion generation and robot action generation under object motion guidance. |
|||||||||
|
ECCV, 2024 (Oral Presentation) 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. |
|||||||||
|
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. |
|||||||||
|
AAAI, 2024 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. |
|||||||||
|
3DV, 2024 project / arXiv / code / data Reconstructing 3D implicit surfaces with accurate, view-independent surface color by decoupling view-dependent shading from geometry. It combines a global color network and a relighting network to preserve volume rendering performance while enabling colored mesh extraction. |
|||||||||
|
ICCV, 2023 project / arXiv / code / 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. |
|||||||||
|
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. |
|||||||||
|
NeurIPS, 2022 - Datasets and Benchmarks Track project / arXiv / code / video A MANO-derived hand model that contains exquisite hand-crafted texture maps, varying in appearance and covering different kinds of blemishes, make-ups, and accessories. |
|||||||||
|
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. |
|||||||||
|
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. |
|||||||||
|
TPAMI, 2024 paper 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. |
|||||||||
|
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. |
|||||||||
|
TPAMI, 2025 arXiv A hybrid inverse kinematics method for 3D body mesh recovery, combining 3D keypoint estimation and body mesh recovery. HybrIK-X extends this to model hands and faces, offering fast, accurate whole-body pose estimation. |
|||||||||
|
CVPR, 2021 project / paper / supp / arXiv / code |
|||||||||
|
BMVC, 2021 paper / arXiv / code |
|||||||||
|
BMVC, 2020 paper / arXiv / code |
|
|
|
CVPR, 2025 project / paper Category-level garment pose tracking via integrated 2D deformation learning and 3D reconstruction. |
|
|
NeurIPS, 2024 paper Part-aware diffusion for articulated object manipulation and controlled image editing in real scenes. |
|
|
|
|
|
|