Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement
Document Type
Conference Proceeding
Publication Date
1-1-2022
Abstract
Low-light images challenge both human perceptions and computer vision algorithms. It is crucial to make algorithms robust to enlighten low-light images for computational photography and computer vision applications such as real-time detection and segmentation. This paper proposes a semantic-guided zero-shot low-light enhancement network (SGZ) which is trained in the absence of paired images, unpaired datasets, and segmentation annotation. Firstly, we design an enhancement factor extraction network using depthwise separable convolution for an efficient estimate of the pixel-wise light deficiency of an low-light image. Secondly, we propose a recurrent image enhancement network to progressively enhance the low-light image with affordable model size. Finally, we introduce an unsupervised semantic segmentation network for preserving the semantic information during intensive enhancement. Extensive experiments on benchmark datasets and a low-light video demonstrate that our model outperforms the previous state-of-the-art. We further discuss the benefits of the proposed method for low-light detection and segmentation. Code is available at https://github.com/ShenZheng2000/SemanticGuided-Low-Light-Image-Enhancement.
Publication Title
Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2022
First Page Number
581
Last Page Number
590
DOI
10.1109/WACVW54805.2022.00064
Recommended Citation
Zheng, Shen and Gupta, Gaurav, "Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement" (2022). Kean Publications. 805.
https://digitalcommons.kean.edu/keanpublications/805