Identity-preserving editing of multiple facial attributes by learning global edit directions and local adjustments

N Mohammadbagheri, F Ayar, A Nickabadi… - Computer Vision and …, 2024 - Elsevier
Semantic facial attribute editing using pre-trained Generative Adversarial Networks (GANs)
has attracted a great deal of attention and effort from researchers in recent years. Due to the …

Disentangled Lifespan Synthesis via Transformer‐Based Nonlinear Regression

M Li, Y Guo - Computer Graphics Forum, 2024 - Wiley Online Library
Lifespan face age transformation aims to generate facial images that accurately depict an
individual's appearance at different age stages. This task is highly challenging due to the …

FLDM-VTON: Faithful Latent Diffusion Model for Virtual Try-on

C Wang, T Chen, Z Chen, Z Huang, T Jiang… - arXiv preprint arXiv …, 2024 - arxiv.org
Despite their impressive generative performance, latent diffusion model-based virtual try-on
(VTON) methods lack faithfulness to crucial details of the clothes, such as style, pattern, and …

Semantic Latent Decomposition with Normalizing Flows for Face Editing

B Li, Z Huang, H Shan, J Zhang - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Navigating in the latent space of StyleGAN has shown effectiveness for face editing.
However, the resulting methods usually encounter challenges in complicated navigation …

Learning Identifiable Concepts for Compositional Image Generation

S Xie, Y Zheng, I Ng, K Zhang - openreview.net
Humans have the ability to decompose objects into parts and relationships and create new
objects by properly combining existing concepts. However, enabling machines to achieve …