Wakeup-Darkness: When Multimodal Meets Unsupervised Low-light Image Enhancement
Zhang, Xiaofeng Xu, Zishan Tang, Hao Gu, Chaochen Chen, Wei El Saddik, Abdulmotaleb
Zhang, Xiaofeng
Xu, Zishan
Tang, Hao
Gu, Chaochen
Chen, Wei
El Saddik, Abdulmotaleb
Supervisor
Department
Computer Vision
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Low-light image enhancement is a crucial visual task, and many unsupervised methods overlook the degradation of visible information in low-light scenes, adversely affecting the fusion of complementary information and hindering the generation of satisfactory results. To address this, we introduce Wakeup-Darkness, a multimodal enhancement framework that innovatively enriches user interaction through voice and textual commands. This approach signifies a technical leap and represents a paradigm shift in user engagement. We introduce a Cross-Modal Feature Fusion (CMFF) that synergizes semantic and depth context with low-light enhancement operations. Moreover, we propose a Gated Residual Block (GRB) and a channel-aware Look-Up Table (LUT) to adjust the intensity distribution of each channel. Crucially, the proposed Wakeup-Darkness scheme demonstrates remarkable generalization in unsupervised scenarios. The source code can be accessed from https://github.com/zhangbaijin/Wakeup-Dakness.
Citation
X. Zhang, Z. Xu, H. Tang, C. Gu, W. Chenand A. El Saddik, “Wakeup-Darkness: When Multimodal Meets Unsupervised Low-Light Image Enhancement”, ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 21, no. 3, pp. 1–25, 2025, doi: 10.1145/3711929.
Source
ACM Transactions on Multimedia Computing, Communications and Applications
Conference
Keywords
Multimodal, low-light image enhancement, segment anything model
Subjects
Source
Publisher
Association for Computing Machinery