Unsupervised Low-light Image Enhancement with Decoupled Networks
- URL: http://arxiv.org/abs/2005.02818v2
- Date: Mon, 28 Mar 2022 05:41:49 GMT
- Title: Unsupervised Low-light Image Enhancement with Decoupled Networks
- Authors: Wei Xiong, Ding Liu, Xiaohui Shen, Chen Fang, Jiebo Luo
- Abstract summary: 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.
- Score: 103.74355338972123
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we tackle the problem of enhancing real-world low-light images
with significant noise in an unsupervised fashion. Conventional unsupervised
learning-based approaches usually tackle the low-light image enhancement
problem using an image-to-image translation model. They focus primarily on
illumination or contrast enhancement but fail to suppress the noise that
ubiquitously exists in images taken under real-world low-light conditions. To
address this issue, we explicitly decouple this task into two sub-tasks:
illumination enhancement and noise suppression. We propose to learn a two-stage
GAN-based framework to enhance the real-world low-light images in a fully
unsupervised fashion. To facilitate the unsupervised training of our model, we
construct samples with pseudo labels. Furthermore, we propose an adaptive
content loss to suppress real image noise in different regions based on
illumination intensity. In addition to conventional benchmark datasets, a new
unpaired low-light image enhancement dataset is built and used to thoroughly
evaluate the performance of our model. Extensive experiments show that our
proposed method outperforms the state-of-the-art unsupervised image enhancement
methods in terms of both illumination enhancement and noise reduction.
Related papers
- Cycle-Interactive Generative Adversarial Network for Robust Unsupervised
Low-Light Enhancement [109.335317310485]
Cycle-Interactive Generative Adversarial Network (CIGAN) is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals.
In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN into the generator of degradation GAN.
arXiv Detail & Related papers (2022-07-03T06:37:46Z) - 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) - Invertible Network for Unpaired Low-light Image Enhancement [78.33382003460903]
We propose to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning.
In addition to the adversarial loss, we design various loss functions to ensure the stability of training and preserve more image details.
We present a progressive self-guided enhancement process for low-light images and achieve favorable performance against the SOTAs.
arXiv Detail & Related papers (2021-12-24T17:00:54Z) - Unsupervised Low-Light Image Enhancement via Histogram Equalization
Prior [40.61944814314655]
We propose an unsupervised low-light image enhancement method based on an effective prior histogram termed equalization prior (HEP)
We introduce a Noise Disentanglement Module (NDM) to disentangle the noise and content in the reflectance maps with the reliable aid of unpaired clean images.
Our method performs favorably against the state-of-the-art unsupervised low-light enhancement algorithms and even matches the state-of-the-art supervised algorithms.
arXiv Detail & Related papers (2021-12-03T07:51:08Z) - CERL: A Unified Optimization Framework for Light Enhancement with
Realistic Noise [81.47026986488638]
Low-light images captured in the real world are inevitably corrupted by sensor noise.
Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step.
We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded framework.
arXiv Detail & Related papers (2021-08-01T15:31:15Z) - Progressive Joint Low-light Enhancement and Noise Removal for Raw Images [10.778200442212334]
Low-light imaging on mobile devices is typically challenging due to insufficient incident light coming through the relatively small aperture.
We propose a low-light image processing framework that performs joint illumination adjustment, color enhancement, and denoising.
Our framework does not need to recollect massive data when being adapted to another camera model.
arXiv Detail & Related papers (2021-06-28T16:43:52Z) - A Two-stage Unsupervised Approach for Low light Image Enhancement [18.365345507072234]
We propose a two-stage unsupervised method that decomposes the low light image enhancement into a pre-enhancement and a post-refinement problem.
Our method can significantly improve feature points matching and simultaneous localization and mapping in low light conditions.
arXiv Detail & Related papers (2020-10-19T08:51:32Z) - Deep Bilateral Retinex for Low-Light Image Enhancement [96.15991198417552]
Low-light images suffer from poor visibility caused by low contrast, color distortion and measurement noise.
This paper proposes a deep learning method for low-light image enhancement with a particular focus on handling the measurement noise.
The proposed method is very competitive to the state-of-the-art methods, and has significant advantage over others when processing images captured in extremely low lighting conditions.
arXiv Detail & Related papers (2020-07-04T06:26:44Z) - Learning an Adaptive Model for Extreme Low-light Raw Image Processing [5.706764509663774]
We propose an adaptive low-light raw image enhancement network to improve image quality.
The proposed method has the lowest Noise Level Estimation (NLE) score compared with the state-of-the-art low-light algorithms.
The potential application in video processing is briefly discussed.
arXiv Detail & Related papers (2020-04-22T09:01:07Z)
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.