EFHQ: Multi-purpose ExtremePose-Face-HQ dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dao, Trung Tuan, Vu, Duc Hong, Pham, Cuong, Tran, Anh
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913311026577408
author Dao, Trung Tuan
Vu, Duc Hong
Pham, Cuong
Tran, Anh
author_facet Dao, Trung Tuan
Vu, Duc Hong
Pham, Cuong
Tran, Anh
contents The existing facial datasets, while having plentiful images at near frontal views, lack images with extreme head poses, leading to the downgraded performance of deep learning models when dealing with profile or pitched faces. This work aims to address this gap by introducing a novel dataset named Extreme Pose Face High-Quality Dataset (EFHQ), which includes a maximum of 450k high-quality images of faces at extreme poses. To produce such a massive dataset, we utilize a novel and meticulous dataset processing pipeline to curate two publicly available datasets, VFHQ and CelebV-HQ, which contain many high-resolution face videos captured in various settings. Our dataset can complement existing datasets on various facial-related tasks, such as facial synthesis with 2D/3D-aware GAN, diffusion-based text-to-image face generation, and face reenactment. Specifically, training with EFHQ helps models generalize well across diverse poses, significantly improving performance in scenarios involving extreme views, confirmed by extensive experiments. Additionally, we utilize EFHQ to define a challenging cross-view face verification benchmark, in which the performance of SOTA face recognition models drops 5-37% compared to frontal-to-frontal scenarios, aiming to stimulate studies on face recognition under severe pose conditions in the wild.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17205
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EFHQ: Multi-purpose ExtremePose-Face-HQ dataset
Dao, Trung Tuan
Vu, Duc Hong
Pham, Cuong
Tran, Anh
Computer Vision and Pattern Recognition
The existing facial datasets, while having plentiful images at near frontal views, lack images with extreme head poses, leading to the downgraded performance of deep learning models when dealing with profile or pitched faces. This work aims to address this gap by introducing a novel dataset named Extreme Pose Face High-Quality Dataset (EFHQ), which includes a maximum of 450k high-quality images of faces at extreme poses. To produce such a massive dataset, we utilize a novel and meticulous dataset processing pipeline to curate two publicly available datasets, VFHQ and CelebV-HQ, which contain many high-resolution face videos captured in various settings. Our dataset can complement existing datasets on various facial-related tasks, such as facial synthesis with 2D/3D-aware GAN, diffusion-based text-to-image face generation, and face reenactment. Specifically, training with EFHQ helps models generalize well across diverse poses, significantly improving performance in scenarios involving extreme views, confirmed by extensive experiments. Additionally, we utilize EFHQ to define a challenging cross-view face verification benchmark, in which the performance of SOTA face recognition models drops 5-37% compared to frontal-to-frontal scenarios, aiming to stimulate studies on face recognition under severe pose conditions in the wild.
title EFHQ: Multi-purpose ExtremePose-Face-HQ dataset
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.17205