Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement

Code

• github.com/caiyuanhao1998/retinexformer
  OfficialIn paperpytorch★ 1,420
• github.com/cmhungsteve/Awesome-Transformer-Attention
  pytorch★ 5,024
• github.com/DmitryRyumin/ICCV-2023-Papers
  none★ 968
• github.com/lcybuzz/Low-Level-Vision-Paper-Record
  tf★ 547
• github.com/dawnlh/awesome-low-light-image-enhancement
  pytorch★ 31

Abstract

When enhancing low-light images, many deep learning algorithms are based on the Retinex theory. However, the Retinex model does not consider the corruptions hidden in the dark or introduced by the light-up process. Besides, these methods usually require a tedious multi-stage training pipeline and rely on convolutional neural networks, showing limitations in capturing long-range dependencies. In this paper, we formulate a simple yet principled One-stage Retinex-based Framework (ORF). ORF first estimates the illumination information to light up the low-light image and then restores the corruption to produce the enhanced image. We design an Illumination-Guided Transformer (IGT) that utilizes illumination representations to direct the modeling of non-local interactions of regions with different lighting conditions. By plugging IGT into ORF, we obtain our algorithm, Retinexformer. Comprehensive quantitative and qualitative experiments demonstrate that our Retinexformer significantly outperforms state-of-the-art methods on thirteen benchmarks. The user study and application on low-light object detection also reveal the latent practical values of our method. Code, models, and results are available at https://github.com/caiyuanhao1998/Retinexformer

Tasks

Benchmark Results

Reproductions