NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI
This work addresses shadow removal in images, which is an incremental improvement for computer vision applications.
The paper tackled the problem of image shadow removal by implementing five improvements to the ShadowFormer model, achieving third place in LPIPS (0.196) and fourth in MOS (7.44) out of 19 teams in the NTIRE 2023 challenge.
In this paper, we analyze and discuss ShadowFormer in preparation for the NTIRE2023 Shadow Removal Challenge [1], implementing five key improvements: image alignment, the introduction of a perceptual quality loss function, the semi-automatic annotation for shadow detection, joint learning of shadow detection and removal, and the introduction of new data augmentation technique "CutShadow" for shadow removal. Our method achieved scores of 0.196 (3rd out of 19) in LPIPS and 7.44 (4th out of 19) in the Mean Opinion Score (MOS).