Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs

This paper addresses 2 challenging tasks: improving the quality of low resolution facial images and accurately locating the facial landmarks on such poor resolution images. To this end, we make the following 5 contributions: (a) we propose Super-FAN: the very first end-to-end system that addresses b...

Full description

Bibliographic Details
Main Authors: Bulat, Adrian, Tzimiropoulos, Georgios
Format: Conference or Workshop Item
Published: 2018
Online Access:https://eprints.nottingham.ac.uk/51131/
_version_ 1848798423930634240
author Bulat, Adrian
Tzimiropoulos, Georgios
author_facet Bulat, Adrian
Tzimiropoulos, Georgios
author_sort Bulat, Adrian
building Nottingham Research Data Repository
collection Online Access
description This paper addresses 2 challenging tasks: improving the quality of low resolution facial images and accurately locating the facial landmarks on such poor resolution images. To this end, we make the following 5 contributions: (a) we propose Super-FAN: the very first end-to-end system that addresses both tasks simultaneously, i.e. both improves face resolution and detects the facial landmarks. The novelty or Super-FAN lies in incorporating structural information in a GAN-based super-resolution algorithm via integrating a sub-network for face alignment through heatmap regression and optimizing a novel heatmap loss. (b) We illustrate the benefit of training the two networks jointly by reporting good results not only on frontal images (as in prior work) but on the whole spectrum of facial poses, and not only on synthetic low resolution images (as in prior work) but also on real-world images. (c) We improve upon the state-of-the-art in face super-resolution by proposing a new residual-based architecture. (d) Quantitatively, we show large improvement over the state-of-the-art for both face super-resolution and alignment. (e) Qualitatively, we show for the first time good results on real-world low resolution images like the ones of Fig. 1.
first_indexed 2025-11-14T20:19:33Z
format Conference or Workshop Item
id nottingham-51131
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T20:19:33Z
publishDate 2018
recordtype eprints
repository_type Digital Repository
spelling nottingham-511312020-05-04T19:41:25Z https://eprints.nottingham.ac.uk/51131/ Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs Bulat, Adrian Tzimiropoulos, Georgios This paper addresses 2 challenging tasks: improving the quality of low resolution facial images and accurately locating the facial landmarks on such poor resolution images. To this end, we make the following 5 contributions: (a) we propose Super-FAN: the very first end-to-end system that addresses both tasks simultaneously, i.e. both improves face resolution and detects the facial landmarks. The novelty or Super-FAN lies in incorporating structural information in a GAN-based super-resolution algorithm via integrating a sub-network for face alignment through heatmap regression and optimizing a novel heatmap loss. (b) We illustrate the benefit of training the two networks jointly by reporting good results not only on frontal images (as in prior work) but on the whole spectrum of facial poses, and not only on synthetic low resolution images (as in prior work) but also on real-world images. (c) We improve upon the state-of-the-art in face super-resolution by proposing a new residual-based architecture. (d) Quantitatively, we show large improvement over the state-of-the-art for both face super-resolution and alignment. (e) Qualitatively, we show for the first time good results on real-world low resolution images like the ones of Fig. 1. 2018-06-18 Conference or Workshop Item PeerReviewed Bulat, Adrian and Tzimiropoulos, Georgios (2018) Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), 18-22 June 2018, Salt Lake City, Utah, USA.
spellingShingle Bulat, Adrian
Tzimiropoulos, Georgios
Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
title Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
title_full Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
title_fullStr Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
title_full_unstemmed Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
title_short Super-FAN: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
title_sort super-fan: integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with gans
url https://eprints.nottingham.ac.uk/51131/