paper-with-me

Papers

Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement

2022-07-03 · Zhangkai Ni, Wenhan Yang, Hanli Wang, Shiqi Wang, Lin Ma, Sam Kwong

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images. However, for unsupervised low light enhancement, the remaining noise suppression issue due to the lacking of supervision of detailed signal largely impedes the wide deployment of these methods in real-world applications. Herein, we propose a novel Cycle-Interactive Generative Adversarial Network (CIGAN) for unsupervised low-light image enhancement, which is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals between two domains, e.g., suppressing/synthesizing realistic noise in the cyclic enhancement/degradation process. In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN (eGAN) into the generator of degradation GAN (dGAN). With the learned information of real low-light images, dGAN can synthesize more realistic diverse illumination and contrast in low-light images. Moreover, the feature randomized perturbation module in dGAN learns to increase the feature randomness to produce diverse feature distributions, persuading the synthesized low-light images to contain realistic noise. Extensive experiments demonstrate both the superiority of the proposed method and the effectiveness of each module in CIGAN.

📄 PDF Abstract BibTeX arXiv:2207.00965

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkImage EnhancementLow-Light Image Enhancement

Similar Papers 제목 키워드 기반

Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval

2019-03-06 · Chao Li, Cheng Deng, Lei Wang, De Xie 외

In recent years, hashing has attracted more and more attention owing to its superior capacity of low storage cost and high query efficiency in large-scale cross-modal retrieval. Benefiting from deep leaning, continuously…

Cross-Modal RetrievalRetrieval

Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks

2018-09-03 · Yuan Yuan, Siyuan Liu, Jiawei Zhang, Yongbing Zhang 외

We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Different from traditional super-resolution formulation, the…

Image Super-ResolutionImage-to-Image TranslationSuper-ResolutionTranslation

Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation

2019-08-02 · Hao Tang, Dan Xu, Gaowen Liu, Wei Wang 외

In this work, we propose a novel Cycle In Cycle Generative Adversarial Network (C$^2$GAN) for the task of keypoint-guided image generation. The proposed C$^2$GAN is a cross-modal framework exploring a joint exploitation …

Generative Adversarial NetworkImage Generation

Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes

2021-06-21 · Hao Tang, Nicu Sebe

We propose a novel and unified Cycle in Cycle Generative Adversarial Network (C2GAN) for generating human faces, hands, bodies, and natural scenes. Our proposed C2GAN is a cross-modal model exploring the joint exploitati…

Generative Adversarial NetworkImage GenerationImage-to-Image TranslationTranslation

Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks

2018-07-23 · ECCV 2018 9 · Minjun Li, Hao-Zhi Huang, Lin Ma, Wei Liu 외

Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss. However, such unsupervised methods may generat…

Image-to-Image TranslationTranslationUnsupervised Image-To-Image Translation