mlsanityData to 7 Oct 2026

NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI

arXiv 2403.08995 ↗First posted 13 Mar 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 21 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

10 of 21 references.

References · 10

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 155
  5. 2019Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GANcited by 102
  6. 2020Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategycited by 66
  7. 2018Task-Driven Super Resolution: Object Detection in Low-resolution Imagescited by 52
  8. 2023ShadowFormer: Global Context Helps Image Shadow Removalcited by 35
  9. 2020NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Resultscited by 18
  10. 2023Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Imagescited by 7

Built on by

Not cited yet.