MGRLN-Net: Mask-Guided Residual Learning Network for Joint Single-Image Shadow Detection and Removal

Leiping Jie, Hui Zhang*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Although significant progress has been made in single-image shadow detection or single-image shadow removal, only few works consider these two problems together. However, the two problems are complementary and can benefit from each other. In this work, we propose a Mask-Guided Residual Learning Network (MGRLN-Net) that jointly estimates shadow mask and shadow-free image. In particular, MGRLN-Net first generates a shadow mask, then utilizes a feature reassembling module to align the features from the shadow detection module to the shadow removal module. Finally, we leverage the learned shadow mask as guidance to generate a shadow-free image. We formulate shadow removal as a masked residual learning problem of the original shadow image. In this way, the learned shadow mask is used as guidance to produce better transitions in penumbra regions. Extensive experiments on ISTD, ISTD+, and SRD benchmark datasets demonstrate that our method outperforms current state-of-the-art approaches on both shadow detection and shadow removal tasks.

Original languageEnglish
Title of host publicationComputer Vision – ACCV 2022
Subtitle of host publication16th Asian Conference on Computer Vision, Macao, China, December 4–8, 2022, Proceedings, Part III
EditorsLei Wang, Juergen Gall, Tat-Jun Chin, Imari Sato, Rama Chellappa
Place of PublicationCham
PublisherSpringer
Pages460-476
Number of pages17
ISBN (Electronic)9783031263132
ISBN (Print)9783031263125
DOIs
Publication statusPublished - 2 Mar 2023
Event16th Asian Conference on Computer Vision, ACCV 2022 - Macao, China
Duration: 4 Dec 20228 Dec 2022
https://link.springer.com/book/10.1007/978-3-031-26319-4 (Conference Proceedings)

Publication series

NameLecture Notes in Computer Science
Volume13843
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameACCV: Asian Conference on Computer Vision

Conference

Conference16th Asian Conference on Computer Vision, ACCV 2022
Country/TerritoryChina
CityMacao
Period4/12/228/12/22
Internet address

Scopus Subject Areas

  • Theoretical Computer Science
  • General Computer Science

User-Defined Keywords

  • Shadow detection and removal
  • Multi-task learning
  • Masked residual learning

Fingerprint

Dive into the research topics of 'MGRLN-Net: Mask-Guided Residual Learning Network for Joint Single-Image Shadow Detection and Removal'. Together they form a unique fingerprint.

Cite this