NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI

Yuki Kondo; Riku Miyata; Fuma Yasue; Taito Naruki; Norimichi Ukita

NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI

Computer Vision and Pattern Recognition 2024-03-18 v2

Authors: Yuki Kondo , Riku Miyata , Fuma Yasue , Taito Naruki , Norimichi Ukita

Abstract

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).

Keywords

image processing competition

Cite

@article{arxiv.2403.08995,
  title  = {NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI},
  author = {Yuki Kondo and Riku Miyata and Fuma Yasue and Taito Naruki and Norimichi Ukita},
  journal= {arXiv preprint arXiv:2403.08995},
  year   = {2024}
}

Comments

This version is a brief technical report submitted to the organizers, and there are still some points to be added; please wait for updates until May 2024. The code can be found here (https://github.com/Yuki-11/NTIRE2023_ShadowRemoval_IIM_TTI)

NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI

Abstract

Keywords

Cite

Comments

Related papers