GAN Prior Embedded Network for Blind Face Restoration in the Wild

Yang, Tao; Ren, Peiran; Xie, Xuansong; Zhang, Lei

doi:10.1109/cvpr46437.2021.00073

Cited by 168 publications

(143 citation statements)

References 26 publications

Supporting

Mentioning

143

Contrasting

Order By: Relevance

“…Note that we focus on the LPIPS scores as it better captures the perceptual quality than other metrics (e.g. PSNR/SSIM) [41,42,48,51,54]. In addition, it can be observed that: in general, methods that learn the degradations, such as DAN and DASR(W), perform much worse than those using manually designed degradation models, which indicates the difficulties in learning complex real-world degradations.…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

“…Although these methods can generate realistic images, they all contain a time-consuming optimization process. Addressing this issue, [3,41,48] propose to learn a posterior distribution with a pretrained StyleGAN generator. Specifically, they learn an encoder to project LR images to a latent space shared with the pretrained generator that outputs HR images.…”

Section: Related Workmentioning

confidence: 99%

“…Although bypassing the needs of explicit HR references, these methods are limited to the domain of the pretrained GANs (e.g. face images [3,48]) and cannot generalize to natural images with diverse contents.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose a novel framework, namely QuanTexSR, for blind SR of natural images. The distinct advantage of our framework is that it addresses the aforementioned limitation of previous works [3,35,41,48] by incorporating quantized texture priors (QTP) that are more suitable for natural image SR. Inspired by the recent VQ-VAE [34,38] and VQGAN [9], we define our QTP as a discrete codebook consisting of a pre-defined number of feature vectors.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors

Chen¹,

Shi²,

Qin³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

A key challenge of blind image super resolution is to recover realistic textures for low-resolution images with unknown degradations. Most recent works completely rely on the generative ability of GANs, which are difficult to train. Other methods resort to high-resolution image references that are usually not available. In this work, we propose a novel framework, denoted as QuanTexSR, to restore realistic textures with the Quantized Texture Priors encoded in Vector Quantized GAN. The QuanTexSR generates textures by aligning the textureless content features to the quantized feature vectors, i.e., a pretrained feature codebook. Specifically, QuanTexSR formulates the texture generation as a feature matching problem between textureless features and a pretrained feature codebook. The final textures are then generated by the quantized features from the codebook. Since features in the codebook have shown the ability to generate natural textures in the pretrain stage, QuanTexSR can generate rich and realistic textures with the pretrained codebook as texture priors. Moreover, we propose a semantic regularization technique that regularizes the pre-training of the codebook using clusters of features extracted from the pretrained VGG19 network. This further improves texture generation with semantic context. Experiments demonstrate that the proposed QuanTexSR can generate competitive or better textures than previous approaches.

show abstract

Section: Comparison With Existing Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors

Chen¹,

Shi²,

Qin³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the latent code for an image, it is possible to navigate in the latent space and modify the produced image. Applications of such latent space navigation include image manipulation [1-3, 37, 40, 43, 48], image restoration [33,37,39,44], and image interpolation [2,31,33,41]. We would like to highlight the work of Zhu et al, which introduced two new embedding spaces for GAN inversion, the P space and the improved P N space [49].…”

Section: Related Workmentioning

confidence: 99%

Art Creation with Multi-Conditional StyleGANs

Dobler¹,

Hübscher²,

Westphal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Creating meaningful art is often viewed as a uniquely human endeavor. A human artist needs a combination of unique skills, understanding, and genuine intention to create artworks that evoke deep feelings and emotions. In this paper, we introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art. Our approach is based on the StyleGAN neural network architecture, but incorporates a custom multi-conditional control mechanism that provides fine-granular control over characteristics of the generated paintings, e.g., with regard to the perceived emotion evoked in a spectator. For better control, we introduce the conditional truncation trick, which adapts the standard truncation trick for the conditional setting and diverse datasets. Finally, we develop a diverse set of evaluation techniques tailored to multi-conditional generation.

show abstract

2D GANs Meet Unsupervised Single-View 3D Reconstruction

Liu

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

GAN Prior Embedded Network for Blind Face Restoration in the Wild

Cited by 168 publications

References 26 publications

Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors

Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors

Art Creation with Multi-Conditional StyleGANs

2D GANs Meet Unsupervised Single-View 3D Reconstruction

Contact Info

Product

Resources

About