|
Ziteng Cui (崔 子藤)
I am a specially appointed assistant professor (特任助教) at the University of Tokyo, affiliated with the MIL Lab at RCAST. I received my Ph.D. from same lab in the University of Tokyo (2025.06), M.S. from Shanghai Jiao Tong University, and B.S. from Harbin Institute of Technology.
I mainly work on Physics-based Vision & Computational Photography & 3D Computer Vision. My favorite things are DOTA2, hiking, anime (JOJO, One Piece, HunterxHunter ...) and Britpop.
My research goal is to integrate physical intrinsic knowledge into real-world downstream applications (e.g., perception, 3D vision, robotics). I'm always open to academic collaborations, feel free to reach out.
Email /
Google Scholar /
Github /
Twitter /
LinkedIn
|
|
举世誉之而不加劝，举世非之而不加沮，定乎内外之分，辩乎荣辱之境，斯已矣。彼其于世，未数数然也。-- 庄子《逍遥游》
|
News
● 2026.03 I received the Dean’s Award from the Graduate School of Engineering (工学系研究科長賞), UTokyo 💐💐
● 2026.02 Two papers (including 1 Finding paper) MERIT and M3A-Policy have been accepted by CVPR 2026, congrats to the team ☀️☀️
● 2026.02 Join the first 3D Restoration and Reconstruction (3DRR) challenge and Efficient Super-Resolution Challenge in CVPR NTIRE workshop 📷📷
● 2025.11 One paper LHSI has been accepted by WACV 2026, congrats to the team ☀️☀️
● 2025.09 Two papers Dr. RAW and I2-NeRF have been accepted by NeurIPS 2025, congrats to the team ☀️☀️
● 2025.09 I have been selected to the Doctoral Consortium at BMVC 2025, and will give an invited talk at BMVC 2025 smart camera workshop 🎙️🎙️
● 2025.08 One paper AR-Talk has been accepted by Siggraph Asia 2025, congrats to the team ☀️☀️
● 2025.06 I successfully defended my Ph.D. dissertation, Dr. Cui now 💐💐
● 2025.04 I have been selected to the Doctoral Consortium at CVPR 2025 ☀️☀️
● 2025.02 One first author paper Luminance-GS has been accepted by CVPR 2025 ☀️☀️
● 2024.08 One first author paper IAC has been accepted by BMVC 2024 ☀️☀️
● 2024.07 One first author paper RAW-Adapter has been accepted by ECCV 2024 ☀️☀️
● 2023.12 One first author paper Aleth-NeRF has been accepted by AAAI 2024 ☀️☀️
● ... ...
|
|
Selected Publications
I'm now interested in the physics modeling of low-level vision and 3D computer vision, I especially interested in the neural radiance field. "*" means authors contribute equally. "#" means corresponding author.
Full publication list please refer to here.
|
|
RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction
Shuhong Liu*, Chenyu Bao*, Ziteng Cui, Yun Liu, Xuangeng Chu, Lin Gu, Marcos V. Conde, Ryo Umagami, Tomohiro Hashimoto, Zijian Hu, Tianhan Xu, Yuan Gan, Yusuke Kurose, Tatsuya Harada.
Arxiv, 2026 [challenge website] [github]
arxiv /
bibtex
|
|
M3APolicy: Mutable Material Manipulation Augmentation Policy through Photometric Re-rendering
Jiayi Li, Yuxan Hu, Haoran Geng, Xiangyu Chen, Chuhao Zhou, Ziteng Cui, Jianfei Yang.
CVPR, 2026 Findings [github]
arxiv /
bibtex
|
|
MERIT: Multi-domain Efficient RAW Image Translation
Wenjun Huang, Shenghao Fu, Yian Jin, Yang Ni, Ziteng Cui, Hanning Chen, Yirui He, Yezi Liu, Sanggeon Yun, SungHeon Jeong, Ryozo Masukawa, William Youngwoo Chung, Mohsen Imani.
CVPR, 2026 [github]
arxiv /
bibtex
|
|
|
Perception-Inspired Color Space Design for Photo White Balance Editing
Yang Cheng, Ziteng Cui#, Lin Gu, Shenghan Su, Zenghui Zhang.
WACV, 2026 [github]
arxiv /
bibtex
|
|
Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task Conditioning
Wenjun Huang*, Ziteng Cui*, Yinqiang Zheng, Yirui He, Tatsuya Harada, Mohsen Imani.
NeurIPS, 2025
arxiv /
bibtex
|
|
I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
Shuhong Liu, Lin Gu, Ziteng Cui, Xuangeng Chu, Tatsuya Harada.
NeurIPS, 2025 [github]
website /
arxiv /
bibtex
|
|
|
Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment
Ziteng Cui#, Xuangeng Chu, Tatsuya Harada.
CVPR, 2025 [github] 
website /
arxiv /
bibtex /
poster
|
|
ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model
Xuangeng Chu, Nabarun Goswami, Ziteng Cui, Hanqin Wang, Tatsuya Harada.
SIGGRAPH ASIA, 2025 [github] 
website /
arxiv /
bibtex
|
|
Discovering an Image-Adaptive Coordinate System for Photography Processing
Ziteng Cui, Lin Gu, Tatsuya Harada.
BMVC, 2024
arxiv /
bibtex
|
|
|
RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images
Ziteng Cui#, Tatsuya Harada.
ECCV, 2024 [github] 
website /
arxiv /
bibtex /
poster
|
|
|
Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption
Ziteng Cui,
Lin Gu, Xiao Sun, Xianzheng Ma, Yu Qiao, Tatsuya Harada.
AAAI, 2024 [github] 
website /
arxiv /
arxiv (old version) /
bibtex /
poster
|
|
Monodetr: Depth-guided transformer for monocular 3d object detection
Renrui Zhang, Han Qiu, Tai Wang, Ziyu Guo, Ziteng Cui, Yu Qiao, Hongsheng Li, Peng Gao
ICCV, 2023 [github] 
arxiv /
bibtex /
code /
poster
|
|
|
You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
Ziteng Cui,
Kunchang Li,
Lin Gu, Shenghan Su, Peng Gao, Zhengkai Jiang, Yu Qiao, Tatsuya Harada.
BMVC, 2022 [github]  (✨ Most Cited in BMVC 2022)
arxiv /
bibtex /
demo /
poster
|
|
Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection
Ziteng Cui,
Yingying Zhu,
Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Renrui Zhang, Zenghui Zhang, Tatsuya Harada.
ECCV, 2022 [github] 
arxiv /
bibtex /
poster
|
|
Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection
Ziteng Cui,
Guo-Jun Qi,
Lin Gu, Shaodi You, Zenghui Zhang, Tatsuya Harada.
ICCV, 2021 [github] 
arxiv /
bibtex /
poster
|
|
Dean’s Award, Graduate School of Engineering, The University of Tokyo, 2026
BMVC 2025 Doctoral Consortium, 2025
CVPR 2025 Doctoral Consortium, 2025
ICCV 2025 Outstanding Reviewer, 2025
CVPR 2025 Outstanding Reviewer, 2025
Ministry of Education of P.R. China National Scholarship, 2022
Shanghai Jiao Tong University Excellent Graduate Student, 2021
|
Reviewer: CVPR, ICCV, ECCV, TPAMI, IJCV, TVCG, ICLR, ICML, NIPS, ACM MM, AISTATS, BMVC, ACCV, WACV, AAAI, Eurographics, Pacific Graphics, TNNLS, TCSVT etc.
|
