Abstract | ||
---|---|---|
Inspired by image-to-curve transformation and multi-exposure fusion, in this paper, we have developed a new method to treat the low light image enhancement tasks as an extended problem with multiple virtual exposures by a non-linear intensity mapping function. Considering that existing image-to-curve methods have difficulty in obtaining the desired detail and brightness recovery in any one iteration without relying on any ground truth, we propose a virtual multi-exposure fusion strategy to merge the outputs from these different iterations. Specifically, a simple CNN is trained to learn a pixel-wise intensity mapping function and accordingly adjust a given image multiple times. Then the results of all iterations are retained together with the original input image for fusion via a WGIF-based Multi-scale pyramid to obtain a final enhanced output. We present experimental results to demonstrate the effectiveness of the new technique and its state-of-the-art performances. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.neucom.2022.08.042 | Neurocomputing |
Keywords | DocType | Volume |
Single image brighten,CNN,Unpaired training,Multi-scale fusion | Journal | 508 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaocheng Wang | 1 | 0 | 0.34 |
Ruimin Hu | 2 | 961 | 117.18 |
Xin Xu | 3 | 162 | 40.08 |