Scholar
Tao Hu
Google Scholar ID: xXUg31EAAAAJ
Research Scientist, PICO,Bytedance
Citations & Impact
Citations
1,094
H-index
11
i10-index
11
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Published numerous papers, including 'EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh,' with several works accepted by top conferences such as NeurIPS, CVPR, and ICCV. Notably, 'Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection' was selected as an ICCV-2023 Best Paper Candidate.
Research Experience
- Prior to joining ByteDance, he worked as a Research Manager (Post-Doctor) at the National University of Singapore (NUS), School of Computing, collaborating with Prof. Lee on 3D Computer Vision. He also founded RealityEdge, which combines large models with interaction for creative work.
Education
- Received the Master's degree from the University of Chinese Academy of Sciences (UCAS) in 2019, supervised by Prof. Honggang Qi; obtained the Bachelor's degree in Automation Engineering from the University of Electronic Science and Technology of China (UESTC) in 2016; and earned his Doctorate from the Department of Computer Science & Engineering at The Chinese University of Hong Kong (CUHK), under the supervision of Prof. Jiaya Jia.
Background
- Currently a Senior Research Scientist at ByteDance Inc. (Pico MR division). His primary research interests lie in 3D Computer Vision and Graphics, particularly focusing on efficient 3D representation, 3D/4D scene generation, 3D rendering, and reconstruction.
