Zero-Reference Low-Light Enhancement via Physical Quadruple Priors
- URL: http://arxiv.org/abs/2403.12933v1
- Date: Tue, 19 Mar 2024 17:36:28 GMT
- Title: Zero-Reference Low-Light Enhancement via Physical Quadruple Priors
- Authors: Wenjing Wang, Huan Yang, Jianlong Fu, Jiaying Liu,
- Abstract summary: We propose a new zero-reference low-light enhancement framework trainable solely with normal light images.
This framework is able to restore our illumination-invariant prior back to images, automatically achieving low-light enhancement.
- Score: 58.77377454210244
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Understanding illumination and reducing the need for supervision pose a significant challenge in low-light enhancement. Current approaches are highly sensitive to data usage during training and illumination-specific hyper-parameters, limiting their ability to handle unseen scenarios. In this paper, we propose a new zero-reference low-light enhancement framework trainable solely with normal light images. To accomplish this, we devise an illumination-invariant prior inspired by the theory of physical light transfer. This prior serves as the bridge between normal and low-light images. Then, we develop a prior-to-image framework trained without low-light data. During testing, this framework is able to restore our illumination-invariant prior back to images, automatically achieving low-light enhancement. Within this framework, we leverage a pretrained generative diffusion model for model ability, introduce a bypass decoder to handle detail distortion, as well as offer a lightweight version for practicality. Extensive experiments demonstrate our framework's superiority in various scenarios as well as good interpretability, robustness, and efficiency. Code is available on our project homepage: http://daooshee.github.io/QuadPrior-Website/
Related papers
- 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) - 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) - Empowering Low-Light Image Enhancer through Customized Learnable Priors [40.83461757842304]
We propose a paradigm for low-light image enhancement that explores the potential of customized learnable priors.
Motivated by the powerful feature representation capability of Masked Autoencoder (MAE), we customize MAE-based illumination and noise priors.
arXiv Detail & Related papers (2023-09-05T05:20:11Z) - 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) - NoiSER: Noise is All You Need for Enhancing Low-Light Images Without
Task-Related Data [103.04999391668753]
We show that it is possible to enhance a low-light image without any task-related training data.
Technically, we propose a new, magical, effective and efficient method, termed underlineNoise underlineSElf-underlineRegression (NoiSER)
Our NoiSER is highly competitive to current task-related data based LLIE models in terms of quantitative and visual results.
arXiv Detail & Related papers (2022-11-09T06:18:18Z) - Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised
Adaptation [36.050270650417325]
We propose a learnable illumination enhancement model for high-level vision.
Inspired by real camera response functions, we assume that the illumination enhancement function should be a concave curve.
Our model architecture and training designs mutually benefit each other, forming a powerful unsupervised normal-to-low light adaptation framework.
arXiv Detail & Related papers (2022-10-07T19:32:55Z) - Learning to Relight Portrait Images via a Virtual Light Stage and
Synthetic-to-Real Adaptation [76.96499178502759]
Relighting aims to re-illuminate the person in the image as if the person appeared in an environment with the target lighting.
Recent methods rely on deep learning to achieve high-quality results.
We propose a new approach that can perform on par with the state-of-the-art (SOTA) relighting methods without requiring a light stage.
arXiv Detail & Related papers (2022-09-21T17:15:58Z) - 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) - Unsupervised Low-light Image Enhancement with Decoupled Networks [103.74355338972123]
We learn a two-stage GAN-based framework to enhance the real-world low-light images in a fully unsupervised fashion.
Our proposed method outperforms the state-of-the-art unsupervised image enhancement methods in terms of both illumination enhancement and noise reduction.
arXiv Detail & Related papers (2020-05-06T13:37:08Z)
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.