Exemplar Guided Face Image Super-Resolution Without Facial Landmarks

@article{Dogan2019ExemplarGF,
  title={Exemplar Guided Face Image Super-Resolution Without Facial Landmarks},
  author={Berk Dogan and Shuhang Gu and R. Timofte},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2019},
  pages={1814-1823}
}
Nowadays, due to the ubiquitous visual media there are vast amounts of already available high-resolution (HR) face images. [...] Key Method GWAInet is trained in an adversarial generative manner to produce the desired high quality perceptual image results. The utilization of the HR guiding image is realized via the use of a warper subnetwork that aligns its contents to the input image and the use of a feature fusion chain for the extracted features from the warped guiding image and the input image. In training…Expand
Facial image super-resolution guided by adaptive geometric features
TLDR
A network including two branches: one for auxiliary depth map estimation and the other for the main SR task, designed to address the traditional issue of restoring a high-resolution facial image from a low-resolution (LR) counterpart. Expand
E-ComSupResNet: Enhanced Face Super-Resolution Through Compact Network
TLDR
A compact and computationally efficient Convolutional Neural Network (CNN) is proposed to increase the spatial resolution of an LR face image to obtain a High-Resolution (HR) face image with an upscaling factor of up to 8 by improving the previous approach. Expand
Robust Super-Resolution of Real Faces using Smooth Features
TLDR
A two module super-resolution network where the feature extractor module extracts robust features from the LR image, and the SR module generates an HR estimate using only these robust features. Expand
E-FCNN for tiny facial expression recognition
TLDR
An edge-aware feedback convolutional neural network (E-FCNN) for tiny FER, which associates image super-resolution and facial expression recognition together and to effectively leverage the texture information of faces, is proposed. Expand
A Deep Learning Approach for Face Hallucination Guided by Facial Boundary Responses
TLDR
An open source Boundary-aware Dual-branch Network is proposed for face hallucination, which simultaneously extracts face features and estimates facial boundary responses from LR inputs, ultimately fusing them to reconstruct HR results. Expand
Blind Face Restoration via Deep Multi-scale Component Dictionaries
TLDR
A deep face dictionary network (termed as DFDNet) to guide the restoration process of degraded observations and can achieve plausible performance in both quantitative and qualitative evaluation, and can generate realistic and promising results on real degraded images without requiring an identity-belonging reference. Expand
Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion
TLDR
To enhance blind face restoration performance by utilizing multi-exemplar images and adaptive fusion of features from guidance and degraded images, multiple adaptive spatial feature fusion (ASFF) layers are introduced to incorporate guidance features in an adaptive and progressive manner. Expand
GAN Prior Embedded Network for Blind Face Restoration in the Wild
TLDR
This work proposes a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior embedded DNN with a set of synthesized low- quality face images. Expand
Image Resolution Susceptibility of Face Recognition Models
TLDR
This work first analyzes the impact of image resolutions on the face verification performance with a state-of-the-art face recognition model, and proposes an evaluation protocol for five well-known datasets, focusing on high, mid, and low-resolution images. Expand
VarSR: Variational Super-Resolution Network for Very Low Resolution Images
TLDR
VarSR, Variational Super Resolution Network, is proposed that matches latent distributions of LR and HR images to recover the missing details and can produce more accurate and perceptually plausible SR images from very low resolutions compared to the deterministic techniques. Expand
...
1
2
...

References

SHOWING 1-10 OF 53 REFERENCES
Face Hallucination with Tiny Unaligned Images by Transformative Discriminative Neural Networks
TLDR
An end-to-end transformative discriminative neural network devised for super-resolving unaligned and very small face images with an extreme upscaling factor of 8.5 and significantly outperforms the state-of-the-art. Expand
Ultra-Resolving Face Images by Discriminative Generative Networks
TLDR
This work presents a discriminative generative network that can ultra-resolve a very low resolution face image of size \(16 \times 16\) pixels to its \(8\times \) larger version by reconstructing 64 pixels from a single pixel. Expand
Learning Warped Guidance for Blind Face Restoration
TLDR
Experiments show that the GFRNet not only performs favorably against the state-of-the-art image and face restoration methods, but also generates visually photo-realistic results on real degraded facial images. Expand
Wavelet-SRNet: A Wavelet-Based CNN for Multi-scale Face Super Resolution
TLDR
A wavelet-based CNN approach that can ultra-resolve a very low resolution face image of 16 × 16 or smaller pixelsize to its larger version of multiple scaling factors in a unified framework with three types of loss: wavelet prediction loss, texture loss and full-image loss is presented. Expand
Learning to Super-Resolve Blurry Face and Text Images
TLDR
This work presents an algorithm to directly restore a clear highresolution image from a blurry low-resolution input and introduces novel training losses that help recover fine details. Expand
Learning Face Hallucination in the Wild
TLDR
A new method of face hallucination is presented, which can consistently improve the resolution of face images even with large appearance variations, based on a novel network architecture called Bi-channel Convolutional Neural Network (Bi-channel CNN). Expand
Deep Learning Face Attributes in the Wild
TLDR
A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently. Expand
Learning Face Representation from Scratch
TLDR
A semi-automatical way to collect face images from Internet is proposed and a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace is built, based on which a 11-layer CNN is used to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF. Expand
Super-Identity Convolutional Neural Network for Face Hallucination
TLDR
This paper defines a super-identity loss to measure the identity difference between a hallucinated face and its corresponding high-resolution face within the hypersphere identity metric space and presents a domain-integrated training approach by constructing a robust identity metric for faces from these two domains. Expand
VGGFace2: A Dataset for Recognising Faces across Pose and Age
TLDR
A new large-scale face dataset named VGGFace2 is introduced, which contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject, and the automated and manual filtering stages to ensure a high accuracy for the images of each identity are described. Expand
...
1
2
3
4
5
...