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

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

Risheng Liu 1,3   Long Ma 2,3    Jiaao Zhang 2,3    Xin Fan 1,3       Zhongxuan Luo 1,3
International School of Information Science & Engineering, Dalian University of Technology 1     
School of Software Technology, Dalian University of Technology 2     
Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province 3     
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.
Flow Chart
Quantitative Comparison
Quantitative Comparison
Qualitative Comparison
Qualitative Comparison
Face Detection
Analysis of Algorithm
Resource
"Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement"
Risheng Liu,  Long Ma,  Jiaao Zhang,   Xin Fan,  Zhongxuan Luo

Accepted by CVPR 2021