Learning Spatial Attention for Face Super-Resolution

• URL: http://arxiv.org/abs/2012.01211v2
• Date: Fri, 4 Dec 2020 12:33:42 GMT
• Title: Learning Spatial Attention for Face Super-Resolution
• Authors: Chaofeng Chen, Dihong Gong, Hao Wang, Zhifeng Li, Kwan-Yee K. Wong
• Abstract summary: General image super-resolution techniques have difficulties in recovering detailed face structures when applying to low resolution face images. Recent deep learning based methods tailored for face images have achieved improved performance by jointly trained with additional task such as face parsing and landmark prediction. We introduce a novel SPatial Attention Residual Network (SPARNet) built on our newly proposed Face Attention Units (FAUs) for face super-resolution.
• Score: 28.60619685892613
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: General image super-resolution techniques have difficulties in recovering detailed face structures when applying to low resolution face images. Recent deep learning based methods tailored for face images have achieved improved performance by jointly trained with additional task such as face parsing and landmark prediction. However, multi-task learning requires extra manually labeled data. Besides, most of the existing works can only generate relatively low resolution face images (e.g., $128\times128$), and their applications are therefore limited. In this paper, we introduce a novel SPatial Attention Residual Network (SPARNet) built on our newly proposed Face Attention Units (FAUs) for face super-resolution. Specifically, we introduce a spatial attention mechanism to the vanilla residual blocks. This enables the convolutional layers to adaptively bootstrap features related to the key face structures and pay less attention to those less feature-rich regions. This makes the training more effective and efficient as the key face structures only account for a very small portion of the face image. Visualization of the attention maps shows that our spatial attention network can capture the key face structures well even for very low resolution faces (e.g., $16\times16$). Quantitative comparisons on various kinds of metrics (including PSNR, SSIM, identity similarity, and landmark detection) demonstrate the superiority of our method over current state-of-the-arts. We further extend SPARNet with multi-scale discriminators, named as SPARNetHD, to produce high resolution results (i.e., $512\times512$). We show that SPARNetHD trained with synthetic data cannot only produce high quality and high resolution outputs for synthetically degraded face images, but also show good generalization ability to real world low quality face images.

Related papers

• W-Net: A Facial Feature-Guided Face Super-Resolution Network [8.037821981254389]
  Face Super-Resolution aims to recover high-resolution (HR) face images from low-resolution (LR) ones. Existing approaches are not ideal due to their low reconstruction efficiency and insufficient utilization of prior information. This paper proposes a novel network architecture called W-Net to address this challenge.
  arXiv  Detail & Related papers  (2024-06-02T09:05:40Z)
• EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection [18.977044046941813]
  In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks. We develop an efficient detector termed EfficientSRFace by introducing a feature-level super-resolution reconstruction network. This module plays an auxiliary role in the training process, and can be removed during the inference without increasing the inference time.
  arXiv  Detail & Related papers  (2023-06-04T06:49:44Z)
• Super-Resolving Face Image by Facial Parsing Information [52.1267613768555]
  Face super-resolution is a technology that transforms a low-resolution face image into the corresponding high-resolution one. We build a novel parsing map guided face super-resolution network which extracts the face prior from low-resolution face image. High-resolution features contain more precise spatial information while low-resolution features provide strong contextual information.
  arXiv  Detail & Related papers  (2023-04-06T08:19:03Z)
• Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors [4.649637261351803]
  We propose a novel recurrent convolutional network based framework for face super-resolution. We take full advantage of the intermediate outputs of the recurrent network, and landmarks information and facial action units (AUs) information are extracted. Our proposed method significantly outperforms state-of-the-art FSR methods in terms of image quality and facial details restoration.
  arXiv  Detail & Related papers  (2022-10-12T08:16:52Z)
• LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network [67.64536397027229]
  Face super-resolution is a challenging and highly ill-posed problem. We propose an end-to-end progressive learning framework incorporating facial attributes. We show that the proposed approach can yield satisfactory face hallucination images outperforming other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-09-29T19:50:45Z)
• Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails [53.080403912727604]
  We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN. It exploits facial geometry priors to replenish and upsample (8*) the occluded and tiny faces. Pro-UIGAN achieves visually pleasing HR faces, reaching superior performance in downstream tasks.
  arXiv  Detail & Related papers  (2021-08-02T02:29:24Z)
• Network Architecture Search for Face Enhancement [82.25775020564654]
  We present a multi-task face restoration network, called Network Architecture Search for Face Enhancement (NASFE) NASFE can enhance poor quality face images containing a single degradation (i.e. noise or blur) or multiple degradations (noise+blur+low-light)
  arXiv  Detail & Related papers  (2021-05-13T19:46:05Z)
• JDSR-GAN: Constructing A Joint and Collaborative Learning Network for Masked Face Super-Resolution [28.022800882214803]
  Face images obtained in most video surveillance scenarios are low resolution with mask simultaneously. Most of the previous face super-resolution solutions can not handle both tasks in one model. We construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task.
  arXiv  Detail & Related papers  (2021-03-25T08:50:40Z)
• Face Super-Resolution Guided by 3D Facial Priors [92.23902886737832]
  We propose a novel face super-resolution method that explicitly incorporates 3D facial priors which grasp the sharp facial structures. Our work is the first to explore 3D morphable knowledge based on the fusion of parametric descriptions of face attributes. The proposed 3D priors achieve superior face super-resolution results over the state-of-the-arts.
  arXiv  Detail & Related papers  (2020-07-18T15:26:07Z)
• DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition [94.96686189033869]
  We propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) DotFAN can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains. Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity.
  arXiv  Detail & Related papers  (2020-02-23T08:16:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.