AI RESEARCH
Winner of CVPR2026 NTIRE Challenge on Image Shadow Removal: Semantic and Geometric Guidance for Shadow Removal via Cascaded Refinement
arXiv CS.CV
•
ArXi:2604.16177v1 Announce Type: new We present a three-stage progressive shadow-removal pipeline for the CVPR2026 NTIRE WSRD+ challenge. Built on OmniSR, our method treats deshadowing as iterative direct refinement, where later stages correct residual artefacts left by earlier predictions. The model combines RGB appearance with frozen DINOv2 semantic guidance and geometric cues from monocular depth and surface normals, reused across all stages. To stabilise multi-stage optimisation, we