Learning Invariant Representation for Unsupervised Image Restoration

@article{Du2020LearningIR,
  title={Learning Invariant Representation for Unsupervised Image Restoration},
  author={Wenchao Du and Hu Chen and Hongyu Yang},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={14471-14480}
}
Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision. Instead, we propose an unsupervised learning method that explicitly learns invariant presentation from noisy data and reconstructs clear observations. To do so, we introduce discrete disentangling representation and adversarial domain adaption into general domain… Expand
Unsupervised Learning Method for Encoder-Decoder-Based Image Restoration
TLDR
This work presents an unsupervised learning algorithm that does not requires paired dataset to train encoder-decoder-like neural network for image restoration and obtains a restored image from the decoder. Expand
Shared Prior Learning of Energy-Based Models for Image Reconstruction
We propose a novel learning-based framework for image reconstruction particularly designed for training without ground truth data, which has three major building blocks: energy-based learning, aExpand
Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images
TLDR
An unsupervised OCT image speckle reduction algorithm that does not rely on well-registered image pairs is proposed that is superior to the classic methods and demonstrates competitive performance to several recently proposed learning-based approaches in both quantitative and qualitative aspects. Expand
CONTRASTIVE REPRESENTATION LEARNING
We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance as representationsExpand
Self-generated Defocus Blur Detection via Dual Adversarial Discriminators
Although existing fully-supervised defocus blur detection (DBD) models significantly improve performance, training such deep models requires abundant pixel-level manual annotation, which is highlyExpand
Generator Pyramid for High-Resolution Image Inpainting
TLDR
This work presents a novel framework -- PyramidFill for high-resolution image inpainting task, which explicitly disentangles content completion and texture synthesis, and demonstrates that PyramidFill generates higher-quality inPainting results than the state-of-the-art methods. Expand
Adaptive noise imitation for image denoising
TLDR
A new Adaptive noise imitation (ADANI) algorithm is developed that can synthesize noisy data from naturally noisy images and is competitive to other networks trained with external paired data. Expand
Federated CycleGAN for Privacy-Preserving Image-to-Image Translation
TLDR
This work proposes a novel federated CycleGAN architecture that can learn image translation in an unsupervised manner while maintaining the data privacy and employs novel switchable generator and discriminator architecture using Adaptive Instance Normalization (AdaIN) that significantly reduces the band-width requirement of the federated learning. Expand
Noise2Grad: Extract Image Noise to Denoise
  • Huangxing Lin, Yihong Zhuang, Yue Huang, Xinghao Ding, Xiaoqing Liu, Yizhou Yu
  • Computer Science
  • IJCAI
  • 2021
TLDR
The proposed method to form the necessary supervision is to extract the noise from the noisy image to synthesize new data, and uses a noise removal module to aid noise extraction to ease the interference of the image background. Expand
Correcting motion artifacts in coronary computed tomography angiography images using a dual-zone cycle generative adversarial network.
TLDR
This study demonstrates that the dual-zone GAN has the excellent ability to correct motion artifacts in the coronary arteries and maintain the overall characteristics of CCTA clinical images. Expand
...
1
2
...

References

SHOWING 1-10 OF 58 REFERENCES
Unsupervised Single Image Deraining with Self-Supervised Constraints
TLDR
An Unsupervised Deraining Generative Adversarial Network (UD-GAN) is proposed to tackle single image deraining problems by introducing self-supervised constraints from the intrinsic statistics of unpaired rainy and clean images. Expand
Unsupervised Image Super-Resolution Using Cycle-in-Cycle Generative Adversarial Networks
TLDR
This work proposes a Cycle-in-Cycle network structure with generative adversarial networks (GAN) as the basic component to tackle the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Expand
Unsupervised Class-Specific Deblurring
TLDR
An end-to-end deblurring network designed specifically for a class of data that learns a strong prior on the clean image domain using adversarial loss and maps the blurred image to its clean equivalent and imposes a scale-space gradient error with an additional gradient module. Expand
Unsupervised Domain-Specific Deblurring via Disentangled Representations
TLDR
This paper presents an unsupervised method for domain-specific, single-image deblurring based on disentangled representations, and enforce a KL divergence loss to regularize the distribution range of extracted blur attributes such that little content information is contained. Expand
Unsupervised Image-to-Image Translation Networks
TLDR
This work makes a shared-latent space assumption and proposes an unsupervised image-to-image translation framework based on Coupled GANs that achieves state-of-the-art performance on benchmark datasets. Expand
DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
TLDR
A novel dual-GAN mechanism is developed, which enables image translators to be trained from two sets of unlabeled images from two domains, and can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data. Expand
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
TLDR
This work presents an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples, and introduces a cycle consistency loss to push F(G(X)) ≈ X (and vice versa). Expand
Coupled Generative Adversarial Networks
TLDR
This work proposes coupled generative adversarial network (CoGAN), which can learn a joint distribution without any tuple of corresponding images, and applies it to several joint distribution learning tasks, and demonstrates its applications to domain adaptation and image transformation. Expand
Image Denoising and Inpainting with Deep Neural Networks
TLDR
A novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA) is presented and can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random. Expand
Deep Image Prior
TLDR
It is shown that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, superresolution, and inpainting. Expand
...
1
2
3
4
5
...