Unsupervised Exposure Correction
This work addresses exposure correction for computer vision applications, offering a more efficient and generalizable solution, though it is incremental as it builds on existing unsupervised and supervised approaches.
The paper tackles the problem of exposure correction in images by introducing an unsupervised method that eliminates the need for manual annotations, improves generalizability, and enhances performance in low-level downstream tasks, outperforming state-of-the-art supervised methods while using only 0.01% of their parameters.
Current exposure correction methods have three challenges, labor-intensive paired data annotation, limited generalizability, and performance degradation in low-level computer vision tasks. In this work, we introduce an innovative Unsupervised Exposure Correction (UEC) method that eliminates the need for manual annotations, offers improved generalizability, and enhances performance in low-level downstream tasks. Our model is trained using freely available paired data from an emulated Image Signal Processing (ISP) pipeline. This approach does not need expensive manual annotations, thereby minimizing individual style biases from the annotation and consequently improving its generalizability. Furthermore, we present a large-scale Radiometry Correction Dataset, specifically designed to emphasize exposure variations, to facilitate unsupervised learning. In addition, we develop a transformation function that preserves image details and outperforms state-of-the-art supervised methods [12], while utilizing only 0.01% of their parameters. Our work further investigates the broader impact of exposure correction on downstream tasks, including edge detection, demonstrating its effectiveness in mitigating the adverse effects of poor exposure on low-level features. The source code and dataset are publicly available at https://github.com/BeyondHeaven/uec_code.