Name
Abstract | ||
|---|---|---|
Though learning-based low-light enhancement methods have achieved significant success, existing methods are still sensitive to noise and unnatural appearance. The problems may come from the lack of structural awareness and the confusion between noise and texture. Thus, we present a low-light image enhancement method that consists of an image disentanglement network and an illumination boosting network. The disentanglement network is first used to decompose the input image into image details and image illumination. The extracted illumination part then goes through a multi-branch enhancement network designed to improve the dynamic range of the image. The multi-branch network extracts multi-level image features and enhances them via numerous subnets. These enhanced features are then fused to generate the enhanced illumination part. Finally, the denoised image details and the enhanced illumination are entangled to produce the normal-light image. Experimental results show that our method can produce visually pleasing images in many public datasets. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/VCIP49819.2020.9301830 | 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP) |
Keywords | DocType | ISSN |
low-light enhancement,image disentanglement,multi-branch enhancement network | Conference | 1018-8770 |
ISBN | Citations | PageRank |
978-1-7281-8069-4 | 0 | 0.34 |
References | Authors | |
10 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nelson Chong Ngee Bow | 1 | 0 | 0.34 |
| Vu-Hoang Tran | 2 | 0 | 1.35 |
| Punchok Kerdsiri | 3 | 0 | 0.34 |
| Yuen Peng Loh | 4 | 0 | 0.34 |
| Ching-Chun Huang | 5 | 7 | 4.91 |