April 23, 2024, 4:47 a.m. | Chenhui Wang, Tao Chen, Zhihao Chen, Zhizhong Huang, Taoran Jiang, Qi Wang, Hongming Shan

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.14162v1 Announce Type: new
Abstract: 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 text. To alleviate these issues caused by the diffusion stochastic nature and latent supervision, we propose a novel Faithful Latent Diffusion Model for VTON, termed FLDM-VTON. FLDM-VTON improves the conventional latent diffusion process in three major aspects. First, we propose incorporating warped clothes as both the starting point and local …

abstract arxiv cs.cv diffusion diffusion model generative nature novel performance stochastic style supervision text type virtual virtual try-on

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

DevOps Engineer (Data Team)

@ Reward Gateway | Sofia/Plovdiv