Domain adaptation for complex shadow removal with shadow transformer network

Woo Jin Ahn, Geon Kang, Hyun Duck Choi, Myo Taeg Lim

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Shadows observed in practical scenes have complex shapes, and removing them is a very challenging task in computer vision. In particular, previous studies on complex shadow removal have limitations in that they can be learned only on paired datasets. Taking the issues into consideration, we present a new domain-adaptive shadow removal framework. The proposed approach includes domain adaptation, detection, and removal stages. The shadow-preserving domain translator in the first stage compensates for the lack of real data through domain transformation of the synthetic data. In the second stage, efficient shadow detection is performed through the domain adaptive mean teacher network. Last, a novel attention network removes complex shadows using detected shadows as a query, effectively removing complex shadows. The feasibility and effectiveness of the proposed framework are validated through the newly collected Grand Theft Auto-Road Shadow dataset. The proposed method outperforms existing methods for quantitative and qualitative metrics related to shadow detection and removal.

Original languageEnglish
Article number126559
JournalNeurocomputing
Volume552
DOIs
Publication statusPublished - 2023 Oct 1

Bibliographical note

Funding Information:
This work was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (Grants No. 2022R1F1A1073543) and was supported by the MSIT(Ministry of Science and ICT), Korea, under the ICAN (ICT Challenge and Advanced Network of HRD) program (IITP-2023-RS-2022-00156385) and the Innovative Human Resource Development for Local Intellectualization support program (IITP-2023-RS-2022-00156287) supervised by the IITP (Institute of Information & Communications Technology Planning & Evaluation).

Publisher Copyright:
© 2023 Elsevier B.V.

Keywords

  • Complex shadow
  • Convolution neural network
  • Domain adaptation
  • Image processing
  • Shadow detection
  • Shadow removal

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Domain adaptation for complex shadow removal with shadow transformer network'. Together they form a unique fingerprint.

Cite this