Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement

TL;DR

This paper introduces RUAS, a lightweight, efficient low-light image enhancement method inspired by Retinex theory, utilizing architecture search to reduce computational complexity while maintaining high performance.

Contribution

The paper presents a novel Retinex-inspired unrolling framework combined with architecture search to automatically discover effective low-light enhancement networks with low computational cost.

Findings

RUAS outperforms recent state-of-the-art methods in low-light image enhancement.

The proposed method achieves high efficiency with fewer computational resources.

Extensive experiments validate the effectiveness and superiority of RUAS.

Abstract

Low-light image enhancement plays very important roles in low-level vision field. Recent works have built a large variety of deep learning models to address this task. However, these approaches mostly rely on significant architecture engineering and suffer from high computational burden. In this paper, we propose a new method, named Retinex-inspired Unrolling with Architecture Search (RUAS), to construct lightweight yet effective enhancement network for low-light images in real-world scenario. Specifically, building upon Retinex rule, RUAS first establishes models to characterize the intrinsic underexposed structure of low-light images and unroll their optimization processes to construct our holistic propagation structure. Then by designing a cooperative reference-free learning strategy to discover low-light prior architectures from a compact search space, RUAS is able to obtain a top-performing image enhancement network, which is with fast speed and requires few computational resources. Extensive experiments verify the superiority of our RUAS framework against recently proposed state-of-the-art methods.