After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data
Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data they rely on have barely changed in nearly a decade. The reason is simple: obtaining a shadow-free target requires removing the occluder while keeping the scene, camera, an...
Shi-Lin Hu, Jing-Yi Xu, Dimitris Samaras et al.
· 0 citations