Shaodi You

Dr. Shaodi You is an Associate Professor at the University of Amsterdam (UvA), working in the Computer Vision Research Group within the Institute of Informatics, Faculty of Science. He received his Ph.D. and M.E. degrees from The University of Tokyo, Japan in 2015 and 2012, and his bachelor's degree from Tsinghua University, P. R. China in 2009.

His research focuses on three main areas: Physics Based Vision, Perception Based Vision and Learning, and 3D geometry. His work specifically addresses challenging problems such as rain and water drop detection/removal, liquid optics, dehazing, and non-rigid 3D geometry. He is particularly known for his work on adherent raindrop detection and removal in video, which was presented at CVPR 2013 and later published in IEEE TPAMI.

His recent publications (2024-2025) demonstrate a strong focus on physics-based vision problems, including rain location prior learning for deraining, generalized segmentation for foggy scenes, and hyperspectral image processing. His research integrates deep learning techniques with physics-based models to solve challenging computer vision problems in adverse conditions. Many of his recent works address weather-related vision challenges, building on his earlier foundational work on raindrop detection.

Dr. You serves as an area chair for major computer vision conferences (CVPR, ICCV, ECCV, and NeurIPS) and is an associate editor of the International Journal of Computer Vision (IJCV). He is the founder of the International Workshop on Physics Based Vision meets Deep Learning (since 2017), which has become an important venue for research at the intersection of physics-based modeling and deep learning in computer vision.

He has supervised students and supported the CSC scholarship program. His research group has developed several important datasets and projects, including GTAV-NightRain, Atlantis, and BUJT-UvA hyperspectral datasets, which have contributed significantly to the computer vision community.