I am currently a second-year master student at Visual & Data Intelligence Center of ShanghaiTech University, supervised by Prof. Lan Xu. I am also fortunate to work closely with Prof. Jingyi Yu and Prof. Jingya Wang. Before graduate study, I received my bachelor degree from ShanghaiTech.
My research interests include:
- 3D computer vision/graphics,
- Human-centric motion understanding,
- LLM-enhanced motion reasoning.
🔥 News
- 2024.02: 🎉🎉 3 papers accepted to CVPR 2024!
- 2023.01: 🎉🎉 1 paper accepted to TVCG 2023!
- 2022.11: 🎉🎉 1 paper accepted to AAAI 2023!
📝 Publications
I’M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions🔗
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Authors: Chengfeng Zhao, Juze Zhang, Jiashen Du, Ziwei Shan, Junye Wang, Jingyi Yu, Jingya Wang, Lan Xu
Abstract: We present I’m-HOI, a monocular scheme to faithfully capture the 3D motions of both the human and object in a novel setting: using a minimal amount of RGB camera and object-mounted Inertial Measurement Unit (IMU).
HOI-M$^3$: Capture Multiple Humans and Objects Interaction within Contextual Environment🔗
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Authors: Juze Zhang*, Jingyan Zhang*, Zining Song, Zhanhe Shi, Chengfeng Zhao, Ye Shi, Jingyi Yu, Lan Xu, Jingya Wang
Abstract: In this paper, we introduce HOI-M$^3$, a novel large-scale dataset for modeling the interactions of Multiple huMans and Multiple objects.
LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment🔗
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Authors: Yiming Ren, Xiao Han, Chengfeng Zhao, Jingya Wang, Lan Xu, Jingyi Yu, Yuexin Ma
Abstract: In this paper, we present LiveHPS, a novel single LiDAR-based approach for scene-level Human Pose and Shape estimation without any limitation of light conditions and wearable devices.
LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors🔗
IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VR), 2023.
Authors: Yiming Ren*, Chengfeng Zhao*, Yannan He, Peishan Cong, Han Liang, Jingyi Yu, Lan Xu, Yuexin Ma
- * represents equal contribution.
Abstract: We propose a multi-sensor fusion method for capturing challenging 3D human motions using single LiDAR and 4 IMUs.
HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions🔗
The 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.
Authors: Han Liang, Yannan He, Chengfeng Zhao, Mutian Li, Jingya Wang, Jingyi Yu, Lan Xu
Abstract: We present a light-weight, hybrid mocap technique called HybridCap that augments the camera with only 4 Inertial Measurement Units (IMUs) in a learning-and-optimization framework.
🏆 Honors and Awards
- Graduate:
- 2024.03 “Outstanding Teaching Assistant”
- 2023.12 “Merit Student”
- Undergraduate:
- 2022.06 “Outstanding Graduate of Shanghai”
- 2022.06 “Outstanding Graduate of ShanghaiTech University”
- 2021.12 “Outstanding Student Leader”
- 2021.12 “Outstanding Student”
- 2020.12 “Merit Student”
💭 Teaching Assistants
- 2023 Fall & 2022 Fall, CS280: Deep Learning, ShanghaiTech University.
- 2022 Spring, CS100: Introduction to Programming, ShanghaiTech University.
- 2021 Fall, CS130: Operating Systems, ShanghaiTech University.
- 2021 Spring, SI100B: Introduction to Information Science and Technology, ShanghaiTech University.
💻 Internships
SenseTime, Shanghai, China.
2021.06 - 2021.09
📖 Educations
High School Affiliated to Nanjing Normal University, Nanjing, China.
2015.09 - 2018.06