Keqiang Sun

About me

I am currently leading a computer vision team in a startup company. We fucus on developing highly controllabe image and video generative models. Previously, I obtained my PhD from Multimedia Laboratory at CUHK, advised by Hongsheng Li and Xiaogang Wang.

Work Experience

Startup Company (Singapore) Team Lead 2024/05 - Present
Reality Lab, Meta (Burlingame, CA) Research Intern 2023/12 - 2024/05
SenseTime (Shanghai) Research Scientist 2020/07 - 2022/06
SenseTime (Beijing) Research Intern 2017/12 - 2020/07

Publications


Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models: Fu-Yun Wang, Yunhao Shui, Jingtan Piao, Keqiang Sun*, Hongsheng Li.; International Conference on Learning Representations (ICLR), 2025; [Paper]


InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation: Zhixin Lai, Keqiang Sun*, Fuyun Wang, Dhritiman Sagar, Erli Ding; International Conference on Learning Representations (ICLR), 2025; [Paper]


🐎 Ponymation: Learning 3D Animal Motions from Unlabeled Online Videos: Keqiang Sun*, Dor Litvak*, Yunzhi Zhang, Hongsheng Li, Jiajun Wu^†, Shangzhe Wu^†.; (*equal contribution, †equal advising); European Conference on Computer Vision (ECCV), 2024; [Paper], [Video], [Project page], [Code]


JourneyDB: A Benchmark for Generative Image Understanding: Keqiang Sun*, Junting Pan*, Yuying Ge, Hao Li, Haodong Duan, Xiaoshi Wu, Renrui Zhang, Aojun Zhou, Zipeng Qin, Yi Wang, Jifeng Dai, Yu Qiao, Limin Wang^†, Hongsheng Li^†; (*equal contribution, †equal advising); Conference on Neural Information Processing Systems (NeurIPS), 2023; [Paper], [Project page], [Code], [HuggingFace], [OpenDataLab],


Human Preference Score: Better Aligning Text-to-Image Models with Human Preference: Xiaoshi Wu, Keqiang Sun, Feng Zhu, Rui Zhao, Hongsheng Li; International Conference on Computer Vision (ICCV), 2023; [Paper], [Project page], [Code],


NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space: Jiawei Yao*, Chuming Li*, Keqiang Sun*, Yingjie Cai, Hao Li, Wanli Ouyang^†, Hongsheng Li^†; (*equal contribution, †equal advising); International Conference on Computer Vision (ICCV), 2023; [Paper], [Project page], [Code]


CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields: Keqiang Sun, Shangzhe Wu, Ning Zhang, Zhaoyang Huang, Quan Wang, Hongsheng Li.; IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023; [Paper], [Project page], [Code]


Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields: Keqiang Sun*, Shangzhe Wu*, Zhaoyang Huang, Ning Zhang, Quan Wang, Hongsheng Li.; (*equal contribution); Conference on Neural Information Processing Systems (NeurIPS), 2022; [Paper], [Project page], [Code]


Inverting Generative Adversarial Renderer for Face Reconstruction: Jingtan Piao, Keqiang Sun, Quan Wang, Kwan-Yee Lin, Hongsheng Li.; Computer Vision and Pattern Recognition (CVPR), 2021 (oral); [Paper], [Project page], [Code]


Aggregation via Separation: Boosting Facial Landmark Detector with Self-Supervised Style Transition: Shengju Qian, Keqiang Sun, Wayne Wu, Chen Qian, Jiaya Jia.; International Conference on Computer Vision (ICCV), 2019; [Paper], [Code]


FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos: Keqiang Sun, Wayne Wu, Tinghao Liu, Shuo Yang, Quan Wang, Qiang Zhou, Zuochang Ye, Chen Qian.; International Conference on Computer Vision (ICCV), 2019; [Paper], [Project page], [Code]

Professional Activities

I serve as a reviewer for: ICCV 2025, ECCV 2024, AAAI 2021; CVPR 2025, 2024, 2021, 2020; ICLR 2022; NeurIPS 2025, 2023, 2022, 2020; ICML 2023; IJCV; Neurocomputing.