NTIRE 2025 Image Shadow Removal Challenge Report
By: Florin-Alexandru Vasluianu , Tim Seizinger , Zhuyun Zhou and more
Potential Business Impact:
Removes shadows from pictures perfectly.
This work examines the findings of the NTIRE 2025 Shadow Removal Challenge. A total of 306 participants have registered, with 17 teams successfully submitting their solutions during the final evaluation phase. Following the last two editions, this challenge had two evaluation tracks: one focusing on reconstruction fidelity and the other on visual perception through a user study. Both tracks were evaluated with images from the WSRD+ dataset, simulating interactions between self- and cast-shadows with a large number of diverse objects, textures, and materials.
Similar Papers
NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results
CV and Pattern Recognition
Fixes blurry or damaged face pictures perfectly.
NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
CV and Pattern Recognition
Helps computers see depth in shiny, see-through things.
NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
CV and Pattern Recognition
Cleans rain from photos, day or night.