Wenjie Li

I am a Ph.D. candidate at Beijing University of Posts and Telecommunications, advised by Prof. Zhanyu Ma and co-advised by Heng Guo. Before starting my Ph.D. phase, I received master's degree at Nanjing University of Posts and Telecommunications in 2023, advised by Prof. Guangwei Gao. I have been fortunate to intern at Megvii Technology.

My research interests include Deep Learning 🧠 and Computer Vision 🤖, particularly focusing on Low-Level Vision 📷, model lightweighting 🚀, and Artificial Intelligence Generated Content (AIGC) 💻.

News

2025/08 -- One co-author paper AMINet got accepted by TSMCA 2025 (CCF-B).
2025/08 -- One paper DMNet got accepted by TMM 2025 (THU-A, CCF-B).
2025/03 -- I have won the 7th place (7/37) in NTIRE 2025 challenge on day and night raindrop removal for dual-focused images as the team leader.
2025/02 -- Our paper CFIN was selected as ESI Highly Cited Paper! (1%)
2024/09 -- One paper FIWHN got accepted by TMM 2024 (THU-A, CCF-B).
2024/07 -- One paper WFEN got accepted by ACM MM 2024 (CCF-A).
2023/10 -- We have released the Awesome-Face-Restoration, collecting comprehensive Face Restoration methods!
2023/05 -- One paper CFIN got accepted by TMM 2023 (THU-A, CCF-B).
2023/04 -- One co-author Survey paper of image super-resolution got accepted by ACM CSUR 2023 (IF=16.6).
2022/04 -- One co-author paper LBNet got accepted by IJCAI 2022 (CCF-A) and selected as short oral.
2021/12 -- One paper FDIWN got accepted by AAAI 2022 (CCF-A).

Selected Publications and Preprints

* Equal contribution. # Corresponding author. Representative papers are highlighted.

Dual-domain Modulation Network for Lightweight Image Super-Resolution
Wenjie Li, Heng Guo#, Yuefeng Hou, Guangwei Gao, Zhanyu Ma
IEEE Transactions on Multimedia (TMM), 2025
arXiv / code / bibtex

FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution
Wenjie Li, Heng Guo#, Yuefeng Hou, Zhanyu Ma
Arxiv:2503.10043 (Under Review), 2025
arXiv / code / 微信公众号 / bibtex

Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network
Wenjie Li, Juncheng Li, Guangwei Gao#, Weihong Deng, Jian Yang, Chia-Wen Lin
IEEE Transactions on Multimedia (TMM), 2024
arXiv / code / bibtex

Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
Wenjie Li, Heng Guo#, Xuannan Liu, Kongming Liang, Jiani Hu, Zhanyu Ma, Jun Guo
ACM Multimedia (ACM MM), 2024
project page / arXiv / code / 知乎 / bibtex

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond
Wenjie Li, Mei Wang, Kai Zhang, Juncheng Li, Xiaoming Li, Yuhang Zhang, Guangwei Gao#, Zhanyu Ma
Arxiv:2309.15490 (Under Review), 2023
project page / arXiv / code / bibtex

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution
Wenjie Li, Juncheng Li, Guangwei Gao#, Weihong Deng, Jian Yang, Guojun Qi
IEEE Transactions on Multimedia (TMM), 2023 (ESI Highly Cited Paper 🏆)
arXiv / code / CCF-导读推荐/ bibtex

Feature Distillation Interaction Weighting Network for Lightweight Image Super-resolution
Guangwei Gao*#, Wenjie Li*, Juncheng Li, Fei Wu, Huimin Lu, Yi Yu
AAAI Conference on Artificial Intelligence (AAAI), 2022
project page / arXiv / code / bibtex

Experience

2022/05 - 2022/11 (Engineer)
Beijing, China

Research Intern

Worked with Qi Xin, where I worked on model lightweighting techniques for 3D human pose estimation models (SPIN), including knowledge distillation and model pruning.

Services and Competitions

Reviewer: ACM MM, AAAI, Knowledge-Based-Systems, Neurocomputing, etc.
7th place (7/37) in Day and Night Raindrop Removal for Dual-Focused Images, CVPR NTIRE 2025, serve as team leader.

Contact