|
Shijian Jiang I am currently pursuing my Ph.D. (Sep. 2022-) in the Control Science and Engineering department at Zhejiang University, advised by Prof. Qi Ye. Before embarking on my doctoral journey, I obtained my B.E. degree at Southeast University. My research mainly focuses on 3D computer vision, especially perceiving 3D hands and objects interaction. |
|
Publications |
|
Dynhor+: Progressive Pose-Shape Optimization for Dynamic Hand-Held Object Reconstruction
Shijian Jiang, Qi Ye, Rengan Xie, Yuchi Huo, Jiming Chen IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2026 Paper / Code Our work progressively optimizes object pose and shape to reconstruct high-fidelity geometry and per-frame 6-DoF poses of dynamically hand-held objects from monocular RGB video. |
|
Contact2Motion: Contact Guided Dexterous Grasp Motion Generation with Synergy Embedded Optimization
Qi Ye, Haoming Li, Qingtao Liu, Shijian Jiang, Tao Zhou, Yuchi Huo, Jiming Chen The International Journal of Robotics Research (IJRR), 2025 Project page / Paper / Code Our work generates dexterous grasp motions through contact reasoning and synergy-embedded optimization, and provides a large-scale synthetic dataset of grasp trajectories. |
|
Hand-held Object Reconstruction from RGB Video with Dynamic Interaction
Shijian Jiang, Qi Ye, Rengan Xie, Yuchi Huo, Jiming Chen CVPR, 2025 Project page / Paper / Code Our work aims to reconstruct the 3D geometry of a rigid object manipulated by one or both hands using monocular RGB video. |
|
In-Hand 3D Object Reconstruction from a Monocular RGB Video
Shijian Jiang, Qi Ye, Rengan Xie, Yuchi Huo, Xiang Li, Yang Zhou, Jiming Chen AAAI, 2024 Project page / Paper Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. |
|
TPGP: Temporal-Parametric Optimization with Deep Grasp Prior for Dexterous Motion Planning
Haoming Li, Qi Ye, Yuchi Huo, Qingtao Liu, Shijian Jiang, Tao Zhou, Xiang Li, Yang Zhou, Jiming Chen ICRA, 2024 Paper |
Projects |
|
3D Hand Reconstruction with GCN
Code |
The website source code from Jon Barron.