Saved in:
Bibliographic Details
Main Authors: Kondo, Yuki, Miyata, Riku, Yasue, Fuma, Naruki, Taito, Ukita, Norimichi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.08995
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917614440153088
author Kondo, Yuki
Miyata, Riku
Yasue, Fuma
Naruki, Taito
Ukita, Norimichi
author_facet Kondo, Yuki
Miyata, Riku
Yasue, Fuma
Naruki, Taito
Ukita, Norimichi
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2403_08995
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI
Kondo, Yuki
Miyata, Riku
Yasue, Fuma
Naruki, Taito
Ukita, Norimichi
Computer Vision and Pattern Recognition
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).
title NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.08995