Bojian Wu

Bojian Wu · 吴博剑

I am a researcher at Tencent. Priorly, I had working experience in Zhejiang University and Alibaba DAMO Academy.

I received my Ph.D. degree in Computer Graphics from University of Chinese Academy of Sciences in 2019, advised by Prof. Hui Huang. From July 2018, I spent half a year in The University of Tokyo, working with Prof. Yonghao Yue and Prof. Takeo Igarashi. I obtained the master's degree from University of Science and Technology of China under the supervision of Prof. Xuejin Chen in 2015. Before that, I got my bachelor's degree from Sichuan University in 2012 (early graduation).

Email / Google Scholar / LinkedIn / Github

Research

I'm interested in computer graphics, image-based 3D reconstruction / modeling / generation. My current works generally focus on how to infer 3D information from 2D images. (co-first author^*, corresponding author^†)

TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
Dongbo Shi, Shen Cao, Lubin Fan, Bojian Wu, Jinhui Guo, Renjie Chen, Ligang Liu, Jieping Ye
arXiv:2502.19800v2
paper / project

Glossy Object Reconstruction with Cost-effective Polarized Acquisition
Bojian Wu, Yifan Peng, Ruizhen Hu, Xiaowei Zhou
CVPR 2025 (Highlight)
paper / project

HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
Jingyu Lin, Jiaqi Gu, Lubin Fan, Bojian Wu, Yujing Lou, Renjie Chen, Ligang Liu, Jieping Ye
CVPR 2025
paper / project / code

CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
Chenghao Zhang, Lubin Fan, Shen Cao, Bojian Wu, Jieping Ye
ICRA 2025
paper

PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
Jinhui Guo, Lubin Fan, Bojian Wu, Jiaqi Gu, Shen Cao, Jieping Ye
ICRA 2025
paper / code

NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior
Dongbo Shi, Shen Cao, Bojian Wu, Jinhui Guo, Lubin Fan, Renjie Chen, Ligang Liu, Jieping Ye
Computer Graphics Forum (Proc. of Eurographics 2025)
to appear ...

Learning Neural Volumetric Pose Features for Camera Localization
Jingyu Lin, Jiaqi Gu, Bojian Wu, Lubin Fan, Renjie Chen, Ligang Liu, Jieping Ye
ECCV 2024
paper / project

Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words
Chuan Tang, Xi Yang, Bojian Wu, Zhizhong Han, Yi Chang
CVPR 2023
paper / code

Homography Loss for Monocular 3D Object Detection
Jiaqi Gu, Bojian Wu^†, Lubin Fan, Jianqiang Huang, Shen Cao, Zhiyu Xiang, Xian-Sheng Hua
CVPR 2022
paper / code

Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis
Jing Ren, Biao Zhang, Bojian Wu, Jianqiang Huang, Lubin Fan, Maks Ovsjanikov, Peter Wonka
ACM Trans. on Graphics (Proc. of SIGGRAPH Asia 2021)
paper / video / code

Survey on 3D Reconstruction of Transparent Objects
Bojian Wu, Hui Huang
Journal of Computer-Aided Design & Computer Graphics (JCAD&CG 2020)
paper (in Chinese) / refer to my Ph.D. dissertation (in Chinese)

Differentiable Refraction-Tracing for Mesh Reconstruction of Transparent Objects
Jiahui Lyu^*, Bojian Wu^*, Dani Lischinski, Daniel Cohen-Or, Hui Huang
ACM Trans. on Graphics (Proc. of SIGGRAPH Asia 2020)
paper / video / code

Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping
Xi Yang, Bojian Wu, Issei Sato, Takeo Igarashi
CVPR 2019 Workshop on Explainable AI
paper

Full 3D Reconstruction of Transparent Objects
Bojian Wu, Yang Zhou, Yiming Qian, Minglun Gong, Hui Huang
ACM Trans. on Graphics (Proc. of SIGGRAPH 2018)
paper / video / code

Learning How Objects Function via Co-Analysis of Interactions
Ruizhen Hu, Oliver van Kaick, Bojian Wu, Hui Huang, Ariel Shamir, Hao Zhang
ACM Trans. on Graphics (Proc. of SIGGRAPH 2016)
paper / video / supp

Last Updated: 2025.04.10 (Template From Here)