CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise

TL;DR

CERL is a unified optimization framework that simultaneously enhances low-light images and suppresses realistic sensor noise, improving visual quality without requiring clean ground-truth images.

Contribution

The paper introduces CERL, a novel integrated approach combining light enhancement and noise suppression into a physics-grounded, plug-and-play optimization framework for real-world noisy low-light images.

Findings

CERL outperforms state-of-the-art methods both qualitatively and quantitatively.

The framework effectively handles spatially variant, intensity-dependent noise.

CERL demonstrates superior results on a new realistic low-light mobile photography dataset.

Abstract

Low-light images captured in the real world are inevitably corrupted by sensor noise. Such noise is spatially variant and highly dependent on the underlying pixel intensity, deviating from the oversimplified assumptions in conventional denoising. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present \underline{C}oordinated \underline{E}nhancement for \underline{R}eal-world \underline{L}ow-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework. For the real low-light noise removal part, we customize a self-supervised denoising model that can easily be adapted without referring to clean ground-truth images. For the light enhancement part, we also improve the design of a state-of-the-art backbone. The two parts are then joint formulated into one principled plug-and-play optimization. Our approach is compared against state-of-the-art low-light enhancement methods both qualitatively and quantitatively. Besides standard benchmarks, we further collect and test on a new realistic low-light mobile photography dataset (RLMP), whose mobile-captured photos display heavier realistic noise than those taken by high-quality cameras. CERL consistently produces the most visually pleasing and artifact-free results across all experiments. Our RLMP dataset and codes are available at: https://github.com/VITA-Group/CERL.