Skip to main content

Research Repository

Advanced Search

Facial reshaping operator for controllable face beautification

Hu, Shanfeng; Shum, Hubert P.H.; Liang, Xiaohui; Li, Frederick W.B.; Aslam, Nauman

Facial reshaping operator for controllable face beautification Thumbnail


Authors

Shanfeng Hu

Xiaohui Liang

Nauman Aslam



Abstract

Posting attractive facial photos is part of everyday life in the social media era. Motivated by the demand, we propose a lightweight method to automatically and efficiently beautify the shapes of both portrait and non-portrait faces in photos, while allowing users to customize the beautification of individual facial features. Previous methods focus on the beautification of mostly frontal and neutral faces, without incorporating user controllability in the beautification process. To address these restrictions, we propose the Facial Reshaping Operator representation, which is affine-invariant, captures the pairwise geometric configuration of facial landmarks, and allows for efficient face beautification with the user-specified weights of individual facial parts. We also propose an unsupervised beautification method in the operator space of faces, where an input face is iteratively pulled towards a local nearby density mode with improved attractiveness. Our method distinguishes itself from the commercial beautification tools in that it mildly enhances facial shapes without altering makeups or complexions, which complements these tools that lack fine-grained control on the attractiveness of facial shapes for users. The experimental results show that our method improves facial shape attractiveness for a large range of poses and expressions, demonstrating the potential of applicability to photos seen on the social media such as Facebook and Instagram everyday.

Citation

Hu, S., Shum, H. P., Liang, X., Li, F. W., & Aslam, N. (2021). Facial reshaping operator for controllable face beautification. Expert Systems with Applications, 167, Article 114067. https://doi.org/10.1016/j.eswa.2020.114067

Journal Article Type Article
Acceptance Date Sep 27, 2020
Online Publication Date Oct 8, 2020
Publication Date Apr 1, 2021
Deposit Date Oct 30, 2020
Publicly Available Date Oct 8, 2021
Journal Expert Systems with Applications
Print ISSN 0957-4174
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 167
Article Number 114067
DOI https://doi.org/10.1016/j.eswa.2020.114067
Public URL https://durham-repository.worktribe.com/output/1252290

Files






You might also like



Downloadable Citations