Name
Abstract | ||
|---|---|---|
Images captured with improper exposures usually bring unsatisfactory visual effects. Previous works mainly focus on either underexposure or overexposure correction, resulting in poor generalization to various exposures. An alternative solution is to mix the multiple exposure data for training a single network. However, the procedures of correcting underexposure and overexposure to normal exposures are much different from each other, leading to large discrepancies for the network in correcting multiple-exposures, thus resulting in poor performance. The key point to address this issue lies in bridging different exposure representations. To achieve this goal, we design a multiple exposure correction framework based on an Exposure Normalization and Compensation (ENC) module. Specifically, the ENC module consists of an exposure normalization part for mapping different exposure features to the exposure-invariant feature space, and a compensation part for integrating the initial features unprocessed by the exposure normalization part to ensure the completeness of information. Besides, to further alleviate the imbalanced performance caused by variations in the optimization process, we introduce a parameter regularization fine-tuning strategy to improve the performance of the worst-performed exposure without degrading other exposures. Our model empowered by ENC outperforms the existing methods by more than 2dB and is robust to multiple image enhancement tasks, demonstrating its effectiveness and generalization capability for real-world applications. Code: https://github.com/KevinJ-Huang/ExposureNorm-Compensation. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/CVPR52688.2022.00595 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
Low-level vision | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jie Huang | 1 | 5 | 0.76 |
| Yajing Liu | 2 | 0 | 0.68 |
| Xueyang Fu | 3 | 354 | 29.09 |
| Man Zhou | 4 | 0 | 1.35 |
| Yang Wang | 5 | 1060 | 72.54 |
| Feng Zhao | 6 | 0 | 4.06 |
| Zhiwei Xiong | 7 | 244 | 46.90 |