Email / Homepage / Google Scholar / Github
I mainly focus on image/video synthesis/editing, 3D generation and low-level vision research, especially on face attributes editing, such as:
- AI for Science
- Video Generation
- 3D Reconstruction/3D Avatar
- Low-level Vision
- ...
We are recruiting full-time engineers. If you are interested, please send an email to my team. Please refer to the website for specific recruitment conditions: Requirements
🚀 News
- 2026-01-25: FastAvatar [Paper] is accepted by ICLR 2026!
- 2025-08-27: The code of FastAvatar [Paper] is avaliable!
- 2024-07-02: One paper accepts by ECCV2024! The code of TinyBeauty [Paper] (ECCV2024) is avaliable!
- 2024-02-27: Two papers are accepted by CVPR2024!
- 2023-12-12: Two papers are accepted by AAAI2024!
- 2023-07-14: One paper is accepted by ICCV2023!
- 2023-04-19: The code of OmniSR [Paper] (CVPR2023) is avaliable!
- 2023-03-24: The code of EQSR [Paper] (CVPR2023) is avaliable!
- 2023-03-22: The code of 3DQD [Paper] (CVPR2023) is avaliable!
- 2023-02-28: Three papers are accepted by CVPR 2023, codes will be avaliable ASAP. 😍
- 2022-11-20: One paper (GeoDSR) accepted by AAAI 2023.
- 2022-09-15: One paper (RainNet) accepted by NeurIPS 2022.
- 2021-12-10: One paper (Bivolution) accepted by AAAI2022.
🌱 Repositories
| Topic | Title | Badge |
|---|---|---|
| Face Attributes Editing | SimSwap: An Efficient Framework For High Fidelity Face Swapping | |
| Face Attributes Editing | SimSwap++: Towards Faster and High-Quality Identity Swapping | |
| Face Attributes Editing | CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing | |
| Style Transfer | Anisotropic Stroke Control for Multiple Artists Style Transfer | |
| High Resolution Face Dataset | VGGFace2-HQ | |
| Efficient Basic Operator | Bi-volution: A Static and Dynamic Coupled Filter | |
| AI for Science | RainNet: A Large-Scale Imagery Dataset and Benchmark for Spatial Precipitation Downscaling | |
| Low-level CV | Learning Continuous Depth Representation via Geometric Spatial Aggregator | |
| Low-level CV | Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit | |
| Low-level CV | Omni Aggregation Networks for Lightweight Image Super-Resolution |