ReCo-Diff: Explore Retinex-Based Condition Strategy in Diffusion Model
for Low-Light Image Enhancement
- URL: http://arxiv.org/abs/2312.12826v1
- Date: Wed, 20 Dec 2023 08:05:57 GMT
- Title: ReCo-Diff: Explore Retinex-Based Condition Strategy in Diffusion Model
for Low-Light Image Enhancement
- Authors: Yuhui Wu, Guoqing Wang, Zhiwen Wang, Yang Yang, Tianyu Li, Peng Wang,
Chongyi Li, Heng Tao Shen
- Abstract summary: Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models.
We propose ReCo-Diff, a novel approach that incorporates Retinex-based prior as an additional pre-processing condition.
- Score: 70.10216029444543
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Low-light image enhancement (LLIE) has achieved promising performance by
employing conditional diffusion models. In this study, we propose ReCo-Diff, a
novel approach that incorporates Retinex-based prior as an additional
pre-processing condition to regulate the generating capabilities of the
diffusion model. ReCo-Diff first leverages a pre-trained decomposition network
to produce initial reflectance and illumination maps of the low-light image.
Then, an adjustment network is introduced to suppress the noise in the
reflectance map and brighten the illumination map, thus forming the learned
Retinex-based condition. The condition is integrated into a refinement network,
implementing Retinex-based conditional modules that offer sufficient guidance
at both feature- and image-levels. By treating Retinex theory as a condition,
ReCo-Diff presents a unique perspective for establishing an LLIE-specific
diffusion model. Extensive experiments validate the rationality and superiority
of our ReCo-Diff approach. The code will be made publicly available.
Related papers
- LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models [39.28266945709169]
We propose a diffusion-based unsupervised framework that incorporates physically explainable Retinex theory with diffusion models for low-light image enhancement.
Experiments on publicly available real-world benchmarks show that the proposed LightenDiffusion outperforms state-of-the-art unsupervised competitors.
arXiv Detail & Related papers (2024-07-12T02:54:43Z) - Distilling Diffusion Models into Conditional GANs [90.76040478677609]
We distill a complex multistep diffusion model into a single-step conditional GAN student model.
For efficient regression loss, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space.
We demonstrate that our one-step generator outperforms cutting-edge one-step diffusion distillation models.
arXiv Detail & Related papers (2024-05-09T17:59:40Z) - Zero-LED: Zero-Reference Lighting Estimation Diffusion Model for Low-Light Image Enhancement [2.9873893715462185]
We propose a novel zero-reference lighting estimation diffusion model for low-light image enhancement called Zero-LED.
It utilizes the stable convergence ability of diffusion models to bridge the gap between low-light domains and real normal-light domains.
It successfully alleviates the dependence on pairwise training data via zero-reference learning.
arXiv Detail & Related papers (2024-03-05T11:39:17Z) - Reti-Diff: Illumination Degradation Image Restoration with Retinex-based
Latent Diffusion Model [59.08821399652483]
Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination.
Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution.
We propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task.
Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RG
arXiv Detail & Related papers (2023-11-20T09:55:06Z) - 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) - Diffusion Models for Image Restoration and Enhancement -- A
Comprehensive Survey [96.99328714941657]
We present a comprehensive review of recent diffusion model-based methods on image restoration.
We classify and emphasize the innovative designs using diffusion models for both IR and blind/real-world IR.
We propose five potential and challenging directions for the future research of diffusion model-based IR.
arXiv Detail & Related papers (2023-08-18T08:40:38Z) - LLDiffusion: Learning Degradation Representations in Diffusion Models
for Low-Light Image Enhancement [118.83316133601319]
Current deep learning methods for low-light image enhancement (LLIE) typically rely on pixel-wise mapping learned from paired data.
We propose a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process.
arXiv Detail & Related papers (2023-07-27T07:22:51Z) - Retinexformer: One-stage Retinex-based Transformer for Low-light Image
Enhancement [96.09255345336639]
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.
arXiv Detail & Related papers (2023-03-12T16:54:08Z)
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.