Selected Publications (Complete list…)
Projects (More projects…)
A unified and user-friendly motion-language model to learn the semantic coupling of two modalities and generate high-quality motions and text descriptions on multiple motion tasks.
Motion Latent Diffusion Models
Human-Object Motion Capture
Using 13 infrared cameras for complex motion capture. We collected a complex motion dataset to assist challenging monocular motion capture for sports video.
Multi-view light stage system for MoCap and 3D Reconstruction.
Dynamic 3D Mesh Player
Stand-alone development work for free-view browsing on 4D scans, which supports 3D mesh rendering, free-angle viewpoint change, Poisson Surface Reconstruction.
I am as a performer for boxing.
Multi-view Dome System
Using more than 72 cameras for dynamic human reconstruction.
Poping result with free view-points.
Avatar with high fidelity clothes and face.
Dome System for static objects
Using more than 80 cameras for multi-view stereo reconstruction. Lead the reconstruction project and aim to build a large 3D mesh sequences dataset.
PCG QQ - Research Scientist
Feb. 2022 - Present
CSIG YouTu Lab -Research Scientist Intern
Nov. 2020 - Mar. 2021
I am working at Tencent, Shanghai and received Tencent STAR Award 2023.
I was a research scientist intern at Tencent YouTu Lab in 2020 focuing on the 3D human body reconstruction.
Sep. 2018 - Feb. 2022
Sep. 2012 - Jul. 2016
I received a B.S. degree in electronic information science and technology and won honorable awards including:
Prof. Jingyi Yu - Supervisor
Prof. Youyi Zheng - Former Supervisor