CAPformer: Compression-Aware Pre-trained Transformer for Low-Light Image Enhancement
This work addresses compression-aware LLIE for resource-constrained phone photography, representing an incremental improvement by focusing on a specific bottleneck.
The paper tackles the problem of low-light image enhancement (LLIE) by addressing the overlooked issue of JPEG compression, which causes information loss in dark areas, and proposes CAPformer with a pre-training strategy and Brightness-Guided Self-Attention to mitigate these effects, demonstrating superiority in experiments.
Low-Light Image Enhancement (LLIE) has advanced with the surge in phone photography demand, yet many existing methods neglect compression, a crucial concern for resource-constrained phone photography. Most LLIE methods overlook this, hindering their effectiveness. In this study, we investigate the effects of JPEG compression on low-light images and reveal substantial information loss caused by JPEG due to widespread low pixel values in dark areas. Hence, we propose the Compression-Aware Pre-trained Transformer (CAPformer), employing a novel pre-training strategy to learn lossless information from uncompressed low-light images. Additionally, the proposed Brightness-Guided Self-Attention (BGSA) mechanism enhances rational information gathering. Experiments demonstrate the superiority of our approach in mitigating compression effects on LLIE, showcasing its potential for improving LLIE in resource-constrained scenarios.