Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Unsupervised Exposure Correction

About

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.

Ruodai Cui, Li Niu, Guosheng Hu• 2025

Related benchmarks

TaskDatasetResultRank
Multi-exposure CorrectionME Dataset Over-exposed
PSNR19.1223
24
Multi-exposure CorrectionME Dataset (Under-exposed)
PSNR18.5293
24
Multi-exposure CorrectionSICE Dataset Over-exposed
PSNR16.5405
23
Exposure CorrectionMSEC Average 12
PSNR18.8258
11
Exposure CorrectionSICE 27 (Average)
PSNR16.7202
11
Exposure CorrectionMSEC
LPIPS0.2309
11
Exposure CorrectionSICE
LPIPS0.3033
11
Exposure CorrectionSICE Under 27
PSNR16.8998
11
Showing 8 of 8 rows

Other info

Follow for update