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

• URL: http://arxiv.org/abs/2303.06705v3
• Date: Thu, 26 Oct 2023 22:19:35 GMT
• Title: Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement
• Authors: Yuanhao Cai, Hao Bian, Jing Lin, Haoqian Wang, Radu Timofte, Yulun Zhang
• Abstract summary: We formulate a principled One-stage Retinex-based Framework (ORF) to enhance low-light images. ORF first estimates the illumination information to light up the low-light image and then restores the corruption to produce the enhanced image. Our algorithm, Retinexformer, significantly outperforms state-of-the-art methods on thirteen benchmarks.
• Score: 96.09255345336639
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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

Related papers

• RSEND: Retinex-based Squeeze and Excitation Network with Dark Region Detection for Efficient Low Light Image Enhancement [1.7356500114422735]
  We propose a more accurate, concise, and one-stage Retinex theory based framework, RSEND. RSEND first divides the low-light image into the illumination map and reflectance map, then captures the important details in the illumination map and performs light enhancement. Our Efficient Retinex model significantly outperforms other CNN-based models, achieving a PSNR improvement ranging from 0.44 dB to 4.2 dB in different datasets.
  arXiv  Detail & Related papers  (2024-06-14T01:36:52Z)
• DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement [73.57965762285075]
  We propose a new expression called Digital-Imaging Retinex theory (DI-Retinex) through theoretical and experimental analysis of Retinex theory in digital imaging. Our proposed method outperforms all existing unsupervised methods in terms of visual quality, model size, and speed.
  arXiv  Detail & Related papers  (2024-04-04T09:53:00Z)
• Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization [21.335003558744496]
  Prior-based methods for low-light image enhancement often face challenges in extracting available prior information from dim images. We introduce a simple yet effective Retinex model with the proposed edge extraction prior. This algorithm addresses the optimization problem associated with the edge-guided Retinex model, enabling effective enhancement of low-light images.
  arXiv  Detail & Related papers  (2024-03-02T09:00:57Z)
• Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation [33.142262765252795]
  Detectors trained on well-lit data exhibit significant performance degradation on low-light data due to low visibility. We propose to boost low-light object detection with zero-shot day-night domain adaptation. Our method generalizes a detector from well-lit scenarios to low-light ones without requiring real low-light data.
  arXiv  Detail & Related papers  (2023-12-02T20:11:48Z)
• Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model [28.762205397922294]
  We propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex. In the Retinex decomposition, we integrate the superiority of attention in Transformer to decompose the image into illumination and reflectance maps. Then, we design multi-path generative diffusion networks to reconstruct the normal-light Retinex probability distribution and solve the various degradations in these components respectively.
  arXiv  Detail & Related papers  (2023-08-25T04:03:41Z)
• Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network [69.96295927854042]
  Low-light environments usually lead to less informative large-scale dark areas. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction.
  arXiv  Detail & Related papers  (2023-08-16T08:46:51Z)
• NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination [48.42173911185454]
  Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. We propose an end-to-end inverse rendering pipeline that decomposes materials and illumination from multi-view images.
  arXiv  Detail & Related papers  (2023-03-29T12:05:19Z)
• Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework [16.579397398441102]
  We design a plug-and-play framework based on the Retinex theory for simultaneously image enhancement and noise removal. Our framework outcompetes the state-of-the-art methods in both image enhancement and denoising.
  arXiv  Detail & Related papers  (2022-10-11T13:29:10Z)
• Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment [50.13230641857892]
  We propose a new deep learning framework for the low-light image enhancement (LIE) problem. The proposed framework contains a decomposition network inspired by algorithm unrolling, and adjustment networks considering both global brightness and local brightness sensitivity. Experiments on a series of typical LIE datasets demonstrated the effectiveness of the proposed method, both quantitatively and visually, as compared with existing methods.
  arXiv  Detail & Related papers  (2022-02-12T03:59:38Z)
• Enhancing Low-Light Images in Real World via Cross-Image Disentanglement [58.754943762945864]
  We propose a new low-light image enhancement dataset consisting of misaligned training images with real-world corruptions. Our model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets.
  arXiv  Detail & Related papers  (2022-01-10T03:12:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.