M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mofayezi, Mohammadreza, Alipour, Reza, Kakavand, Mohammad Ali, Asgari, Ehsaneddin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910318550056960
author Mofayezi, Mohammadreza
Alipour, Reza
Kakavand, Mohammad Ali
Asgari, Ehsaneddin
author_facet Mofayezi, Mohammadreza
Alipour, Reza
Kakavand, Mohammad Ali
Asgari, Ehsaneddin
contents Human face generation and editing represent an essential task in the era of computer vision and the digital world. Recent studies have shown remarkable progress in multi-modal face generation and editing, for instance, using face segmentation to guide image generation. However, it may be challenging for some users to create these conditioning modalities manually. Thus, we introduce M3Face, a unified multi-modal multilingual framework for controllable face generation and editing. This framework enables users to utilize only text input to generate controlling modalities automatically, for instance, semantic segmentation or facial landmarks, and subsequently generate face images. We conduct extensive qualitative and quantitative experiments to showcase our frameworks face generation and editing capabilities. Additionally, we propose the M3CelebA Dataset, a large-scale multi-modal and multilingual face dataset containing high-quality images, semantic segmentations, facial landmarks, and different captions for each image in multiple languages. The code and the dataset will be released upon publication.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02369
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing
Mofayezi, Mohammadreza
Alipour, Reza
Kakavand, Mohammad Ali
Asgari, Ehsaneddin
Computer Vision and Pattern Recognition
Computation and Language
Multimedia
Human face generation and editing represent an essential task in the era of computer vision and the digital world. Recent studies have shown remarkable progress in multi-modal face generation and editing, for instance, using face segmentation to guide image generation. However, it may be challenging for some users to create these conditioning modalities manually. Thus, we introduce M3Face, a unified multi-modal multilingual framework for controllable face generation and editing. This framework enables users to utilize only text input to generate controlling modalities automatically, for instance, semantic segmentation or facial landmarks, and subsequently generate face images. We conduct extensive qualitative and quantitative experiments to showcase our frameworks face generation and editing capabilities. Additionally, we propose the M3CelebA Dataset, a large-scale multi-modal and multilingual face dataset containing high-quality images, semantic segmentations, facial landmarks, and different captions for each image in multiple languages. The code and the dataset will be released upon publication.
title M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing
topic Computer Vision and Pattern Recognition
Computation and Language
Multimedia
url https://arxiv.org/abs/2402.02369