I received the Ph.D. degree from Nanjing University (NJU), 2025, under the supervision of Prof. Tong Lu, and working closely with Dr. Wenhan Luo and Dr. Kaihao Zhang. Previously, I obtained my master’s degree in 2021 under the supervision of Prof. Xiaoqin Zhang. From September 2024 to March 2025, I worked as an academic intern at VIVO (Shanghai). I have published over 40 peer-reviewed papers in top-tier journals and conferences, like IJCV, TIP, ICCV, ECCV, NeurIPS, SIGGRAPH, AAAI, IJCAI, ACM MM, etc. I am a reviewer for TPAMI, TIP, CVPR, ICCV, ECCV, NeurIPS, SIGGRAPH, ICLR, AAAI, IJCAI, etc.

Here is my [CV], and you can contact me by E-mail:

Research

I am interested in several topics in computer vision and machine learning. Specifically, my research focuses on creative AI, such as image/video enhancement and synthesis, AI generated content (AIGC).

Updates

2025/07 - One paper was accepted by ECAI 2025 (correspondence pruning).

2025/06 - Two papers were accepted by ICCV 2025 (MOERL and MaterialMVP).

2025/05 - Successfully defended PhD dissertation.

2025/04 - One paper was accepted by SIGGRAPH 2025 (video super-resolution).

2025/03 - One paper was accepted by PR (low-light enhancement).

2024/12 - One paper was accepted by PR (face restoration).

2024/12 - Two papers were accepted by ICASSP 2025 (face enhancement, UDC image restoration).

2024/11 - BYD scholarship.

2024/08 - One paper was accepted by TCSVT (face Anti-spoofing).

2024/07 - One paper was accepted by ACM MM 2024 (video face restoration).

2024/07 - One paper was accepted by ECAI 2024 (correspondence pruning).

2024/07 - One paper was accepted by ECCV 2024 (personalized text-to-image generation).

2024/03 - One paper was accepted by TCSVT (blind face restoration).

2024/03 - One paper was accepted by IJCV (adverse weather restoration).

2023/12 - One paper was accepted by AAAI 2024 (correspondence pruning).

2023/11 - One paper was accepted by TCSVT (under-display camera face image restoration).

2023/11 - Sun-Xiangzhen scholarship of Nanjing University.

2023/09 - One paper was accepted by NeurIPS 2023 (punctuation-level attack for text models).

2023/09 - One paper was accepted by TCSVT (a comprehensive benchmark for image deblurring).

2023/09 - One paper was accepted by PR (image dehazing).

2023/04 - One paper was accepted by IJCAI 2023 (graph representation learning).

2023/04 - One paper was accepted by TCSVT (rgb-d salient object detection).

2023/01 - One paper was selected for an ORAL presentation at AAAI 2023 (UHD low-light enhancement).

2022/11 - One paper was accepted by AAAI 2023 (UHD low-light enhancement).

2022/11 - One paper was online in Arxiv (face restoration survey), see the news.

Recent Projects

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration,
T. Wang, P. Xia, B. Li, P. Jiang, Z. Kong, K. Zhang, T. Lu, W. Luo
Proc. of International Conference on Computer Vision (ICCV), 2025. (Top Conference)

A general backbone with RL for image restoration in adverse weather conditions.


GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions,
T. Wang, K. Zhang, Z. Shao, W. Luo, B. Stenger, T. Lu, TK. Kim, W. Liu, H. Li
International Journal of Computer Vision (IJCV), 2024. (Top Journal)

A general Transformer backbone for image restoration in adverse weather conditions.


Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method,
T. Wang, K. Zhang, T. Shen, W. Luo, B. Stenger, T. Lu,
Proc. of the Association for the Advancement of Artificial Intelligence (AAAI), 2023. (ORAL)

The first work proposing the UHD-LLIE problem and addressing it with transformer.


Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning,
T. Wang, G. Tao, W. Lu, K. Zhang, W. Luo, X. Zhang, T. Lu,
Pattern Recognition (PR), 2023.

A framework using contrastive learning to produce visually pleasing images.


LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement,
T. Wang, K. Zhang, Y. Zhang, W. Luo, B. Stenger, T. Lu, TK. Kim, W. Liu,
Pattern Recognition (PR), 2025.

Enhancement with diffusion model and degradation learning.


Video Deblurring via Spatiotemporal Pyramid Network and Adversarial Gradient Prior,
T. Wang, X. Zhang, R. Jiang, L. Zhao, H. Chen, W. Luo,
Computer Vision and Image Understanding (CVIU), 2021.

Video deblurring with spatiotemporal learning and adversarial gradient prior.


Multi-level Fusion and Attention-guided CNN for Image Dehazing,
X. Zhang, T. Wang*, W. Luo, P. Huang,
IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), 2021. (ESI Highly Cited Paper)

A unified framework for image dehazing using multi-level fusion and attetnion mechanism.

Professional Activities

Conference Reviewer: CVPR, ECCV, ICCV, NeurIPS, ICLR, SIGGRAPH, AAAI, IJCAI, ACM MM, etc.

Journal Reviewer: TPAMI, TIP, TCSVT, CVIU, TII, TMM, ITS, NN, etc.

Visitors