Controllable and Gradual Facial Blemishes Retouching via Physics-Based Modelling

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shuai, Chenhao, Cai, Rizhao, Dissanayake, Bandara, Newman, Amanda, Guan, Dayan, Sng, Dennis, Li, Ling, Kot, Alex
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911926119825408
author Shuai, Chenhao
Cai, Rizhao
Dissanayake, Bandara
Newman, Amanda
Guan, Dayan
Sng, Dennis
Li, Ling
Kot, Alex
author_facet Shuai, Chenhao
Cai, Rizhao
Dissanayake, Bandara
Newman, Amanda
Guan, Dayan
Sng, Dennis
Li, Ling
Kot, Alex
contents Face retouching aims to remove facial blemishes, such as pigmentation and acne, and still retain fine-grain texture details. Nevertheless, existing methods just remove the blemishes but focus little on realism of the intermediate process, limiting their use more to beautifying facial images on social media rather than being effective tools for simulating changes in facial pigmentation and ance. Motivated by this limitation, we propose our Controllable and Gradual Face Retouching (CGFR). Our CGFR is based on physical modelling, adopting Sum-of-Gaussians to approximate skin subsurface scattering in a decomposed melanin and haemoglobin color space. Our CGFR offers a user-friendly control over the facial blemishes, achieving realistic and gradual blemishes retouching. Experimental results based on actual clinical data shows that CGFR can realistically simulate the blemishes' gradual recovering process.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13227
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Controllable and Gradual Facial Blemishes Retouching via Physics-Based Modelling
Shuai, Chenhao
Cai, Rizhao
Dissanayake, Bandara
Newman, Amanda
Guan, Dayan
Sng, Dennis
Li, Ling
Kot, Alex
Computer Vision and Pattern Recognition
Face retouching aims to remove facial blemishes, such as pigmentation and acne, and still retain fine-grain texture details. Nevertheless, existing methods just remove the blemishes but focus little on realism of the intermediate process, limiting their use more to beautifying facial images on social media rather than being effective tools for simulating changes in facial pigmentation and ance. Motivated by this limitation, we propose our Controllable and Gradual Face Retouching (CGFR). Our CGFR is based on physical modelling, adopting Sum-of-Gaussians to approximate skin subsurface scattering in a decomposed melanin and haemoglobin color space. Our CGFR offers a user-friendly control over the facial blemishes, achieving realistic and gradual blemishes retouching. Experimental results based on actual clinical data shows that CGFR can realistically simulate the blemishes' gradual recovering process.
title Controllable and Gradual Facial Blemishes Retouching via Physics-Based Modelling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.13227