Bohan Li' Homepage (original) (raw)

Biography

I'm a Ph.D. student at Shanghai Jiao Tong University (SJTU) and Eastern Institute for Advanced Study (EIAS), advised by Prof. Xin Jin, Prof. Wenjun Zeng, Prof. Chao Ma, and Prof. Xiaokang Yang. My research interests lie in esearch interest in 3D computer vison, especially focusing on 3D scene comprehension and multi-modal genration. Before joining SJTU, I was a computer vision algorithm engineer at Tencent AI Lab, working on large-sclale 3D city scene generation and reconstruction. I did my Master degree at South China University of Technology (SCUT) and Bachelor degree at Northeastern University (NEU). I have also spent some time at BAAI, Lixiang, MEGVII Research, IDEA, NetEase AILab, PhiGent Robtics, ZTE Corporation.

Research

I have a broad research interest in 3D computer vison, including Autonomous Vehicles and Robotics, 3D Scene Comprehension and Generation, 3D Structed Information Processing, Representation Disentanglement, Explainability of AI systems.

News

Selected Publications

UniScene: Unified Occupancy-centric Driving Scene Generation Bohan Li, Jiazhe Guo, Hongsi Liu, Yingshuang Zou, Yikang Ding, Xiwu Chen, Hu Zhu, Feiyang Tan, Chi Zhang, Tiancai Wang, Shuchang Zhou, Li Zhang, Xiaojuan Qi, Hao Zhao, Mu Yang, Wenjun Zeng, Xin Jin. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025) [ paper ] [ project page ] [ code ]
TAPTRv2: Attention-based Position Update Improves Tracking Any Point Hongyang Li, Feng Li, Hao Zhang, Tianhe Ren, Shilong Liu, Bohan Li, Zhaoyang Zeng, Lei Zhang. Neural Information Processing Systems (NeurIPS 2025) [paper ]
Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion Bohan Li, Jiajun Deng, Wenyao Zhang, Liang, Dalong Du, Xin Jin, and Wenjun Zeng. European Conference on Computer Vision (ECCV 2024) [paper ] [ code ]
Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedback Xin Jin, Bohan Li, Baao Xie, Wenyao Zhang, Jinming Liu, Ziqiang Li, Tao Yang, Wenjun Zeng. European Conference on Computer Vision (ECCV 2024) [paper ]
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion Bohan Li, Yasheng Sun, Zhujin Liang, Dalong Du, Zhuanghui Zhang, Xiaofeng Wang, Yunnan Wang, Xin Jin, Wenjun Zeng. International Joint Conference on Artificial Intelligence (IJCAI 2024) [paper ] [ code ]
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception Bohan Li, Yasheng Sun, Jingxin Dong, Zheng Zhu, Jinming Liu, Xin Jin, Wenjun Zeng. AAAI Conference on Artificial Intelligence (AAAI 2024) [paper ]
NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation Baao Xie, Bohan Li, Zequn Zhang, Junting Dong, Xin Jin, Jingyu Yang, Wenjun Zeng. International Conference on Computer Vision (ICCV 2023) [paper ] [ code ]
Robust Scale-Aware Stereo Matching Network James Okae, Bohan Li, Juan Du, Yueming Hu. IEEE Transactions on Artificial Intelligence (TAI) [paper ]

Experiences

BAAI Project leader & Research Intern Topic: Large-scale 4D reconstruction and generation
Lixiang Project leader & Research Intern Topic: Scalable Multi-modal Driving Scene Generation
MEGVII Project leader & Research Intern Topic: UniScene: Unified Occupancy-centric Driving Scene Generation
IDEA Research Intern Topic: Occupancy-based scene generation, Long-term consistent perception
Tencent AILab Full-time Research Engineer Topic: Large-scale 3D city scene generation and reconstruction
NetEase AILab Research Intern Topic: Robust 3D perception and reconstruction
PhiGent Robotics Engineer & Research Intern Topic: Semantic Scene Completion, Depth estimation, Stereo Matching
ZTE Research Intern Topic: Monocular Depth estimation, Real-time Stereo Matching

Academic Services

© Bohan Li | Last updated: March, 2025