Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Controllable facial attribute editing via Gaussian mixture model disentanglement

Li, Bo, Deng, Shu-Hai, Liu, Bin, Li, Yike, He, Zhi-Fen, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680, Zhang, Congxuan and Chen, Zhen 2023. Controllable facial attribute editing via Gaussian mixture model disentanglement. Digital Signal Processing 134 , 103916. 10.1016/j.dsp.2023.103916

[thumbnail of Controllable_Facial_Attribute_Editing_via_Gaussian_Mixture_Model_Disentanglement_DSP.pdf]
Preview
PDF - Accepted Post-Print Version
Download (36MB) | Preview

Abstract

Generative adversarial networks (GANs) have made much progress in the field of high-quality and realistic facial image synthesis in recent years. However, compared with their powerful generation ability, it is difficult for users to modify the desired attributes of the resulting image while keeping the others. How to disentangle the latent space of pre-trained GANs is essential and critical for controllable image synthesis. In this paper, a novel controllable facial attribute editing algorithm based on the Gaussian mixture model (GMM) representation is proposed. First, we assume that the latent variables with respect to each facial attribute lie in a subspace of the whole latent manifold composed of a fixed number of learned features, and each attribute subspace can be modeled by a GMM. Then, to avoid unintended changes during attribute editing, a coordinate accumulation strategy with orthogonal regularization is introduced to enhance the independence of distinct attribute subspaces which helps improving the controllability of attribute editing. In addition, a resampling strategy is utilized to improve the stability of the model. Through qualitative and quantitative experimental results, the proposed method achieves the state-of-the-art performance on facial attribute editing, and improves the controllability of desired attribute editing.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Engineering
Publisher: Elsevier
ISSN: 1051-2004
Date of First Compliant Deposit: 14 February 2023
Date of Acceptance: 3 January 2023
Last Modified: 11 Jan 2024 08:38
URI: https://orca.cardiff.ac.uk/id/eprint/156915

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics