Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement
This work addresses the problem of high computational burden and significant architecture engineering for low-light image enhancement, which is important for real-world applications requiring fast processing and limited resources.
This paper proposes Retinex-inspired Unrolling with Architecture Search (RUAS) to create a lightweight and effective network for low-light image enhancement. RUAS models underexposed image structures based on the Retinex rule and uses a cooperative reference-free learning strategy to discover efficient prior architectures, resulting in a fast and computationally inexpensive enhancement network.
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.