Scholar
Bohan Li
Google Scholar ID: V-YdQiAAAAAJ
Shanghai Jiao Tong University
Citations & Impact
Citations
196
H-index
9
i10-index
8
Publications
20
Co-authors
19
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published papers:
- - OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation (IEEE TPAMI)
- - OmniNWM: Omniscient Driving Navigation World Models (Arxiv)
- - UniScene: Unified Occupancy-centric Driving Scene Generation (CVPR 2025)
- - NaviNeRF++: Towards Interpretable 3D Reconstruction via Unsupervised Disentangled Representation Learning (IEEE TPAMI)
- - Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method (Arxiv)
- - Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond (Arxiv)
- - ORV: 4D Occupancy-centric Robot Video Generation (Arxiv)
Research Experience
- Worked as a Computer Vision Algorithm Engineer at Tencent AI Lab, focusing on large-scale 3D city scene generation and reconstruction. Involved in multiple research projects including OmniNWM, UniScene, etc.
Education
- Ph.D. student at Shanghai Jiao Tong University (SJTU) and Eastern Institute of Technology (EIT), Ningbo, advised by Prof. Xin Jin, Prof. Wenjun Zeng, Prof. Chao Ma, and Prof. Xiaokang Yang; Master's degree from South China University of Technology (SCUT); Bachelor's degree from Northeastern University (NEU). Also, a Visiting Scholar at the National University of Singapore (NUS) in the Department of Biomedical Engineering and Department of Electrical and Computer Engineering, working with Prof. Yueming Jin, and closely collaborated with Prof. Hao Zhao at Tsinghua University.
Background
- Research interest in 3D computer vision, especially focusing on 3D scene comprehension and multi-modal generation. Previously worked as a Computer Vision Algorithm Engineer at Tencent AI Lab, working on large-scale 3D city scene generation and reconstruction.
Miscellany
- Personal interests not mentioned
