Open AccessProceedings Article
Face Hallucination with Tiny Unaligned Images by Transformative Discriminative Neural Networks
Xin Yu,Fatih Porikli +1 more
- Vol. 31, Iss: 1, pp 4327-4333
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.Abstract:
Conventional face hallucination methods rely heavily on accurate alignment of low-resolution (LR) faces before upsampling them. Misalignment often leads to deficient results and unnatural artifacts for large upscaling factors. However, due to the diverse range of poses and different facial expressions, aligning an LR input image, in particular when it is tiny, is severely difficult. To overcome this challenge, here we present an end-to-end transformative discriminative neural network (TDN) devised for super-resolving unaligned and very small face images with an extreme upscaling factor of 8. Our method employs an upsampling network where we embed spatial transformation layers to allow local receptive fields to line-up with similar spatial supports. Furthermore, we incorporate a class-specific loss in our objective through a successive discriminative network to improve the alignment and upsampling performance with semantic information. Extensive experiments on large face datasets show that the proposed method significantly outperforms the state-of-the-art.read more
Citations
More filters
Journal ArticleDOI
Deep Learning for Image Super-Resolution: A Survey
TL;DR: A survey on recent advances of image super-resolution techniques using deep learning approaches in a systematic way, which can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR.
Proceedings ArticleDOI
Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes
TL;DR: An attribute-embedded upsampling network that can super-resolve tiny (16×16 pixels) unaligned face images with a large upscaling factor of 8× while reducing the uncertainty of one-to-many mappings remarkably is developed.
Book ChapterDOI
Face Super-resolution Guided by Facial Component Heatmaps
TL;DR: This paper proposes a method that explicitly incorporates structural information of faces into the face super-resolution process by using a multi-task convolutional neural network (CNN) and achieves superior face hallucination results and outperforms the state-of-the-art.
Journal ArticleDOI
Face Hallucination Using Cascaded Super-Resolution and Identity Priors
TL;DR: In this article, a cascaded super-resolution network with identity priors was proposed to hallucinate high-resolution facial images from low-resolution inputs at high magnification factors, which achieved state-of-the-art performance on the Labeled Faces in the Wild (LFW) and CelebA datasets.
Book ChapterDOI
Learning Warped Guidance for Blind Face Restoration
TL;DR: 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.
References
More filters
Posted Content
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TL;DR: This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.
Proceedings ArticleDOI
Deep Learning Face Attributes in the Wild
TL;DR: 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.
Proceedings Article
Spatial transformer networks
TL;DR: This work introduces a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network, and can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps.
Journal ArticleDOI
Image Super-Resolution Using Deep Convolutional Networks
TL;DR: Zhang et al. as discussed by the authors proposed a deep learning method for single image super-resolution (SR), which directly learns an end-to-end mapping between the low/high-resolution images.
Journal ArticleDOI
Image Super-Resolution Via Sparse Representation
TL;DR: This paper presents a new approach to single-image superresolution, based upon sparse signal representation, which generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods.