Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Leyang, Lin, Joice
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2503.16376
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908521690300416
author Wang, Leyang
Lin, Joice
author_facet Wang, Leyang
Lin, Joice
contents The success of modern machine learning, particularly in facial translation networks, is highly dependent on the availability of high-quality, paired, large-scale datasets. However, acquiring sufficient data is often challenging and costly. Inspired by the recent success of diffusion models in high-quality image synthesis and advancements in Large Language Models (LLMs), we propose a novel framework called LLM-assisted Paired Image Generation (LaPIG). This framework enables the construction of comprehensive, high-quality paired visible and thermal images using captions generated by LLMs. Our method encompasses three parts: visible image synthesis with ArcFace embedding, thermal image translation using Latent Diffusion Models (LDMs), and caption generation with LLMs. Our approach not only generates multi-view paired visible and thermal images to increase data diversity but also produces high-quality paired data while maintaining their identity information. We evaluate our method on public datasets by comparing it with existing methods, demonstrating the superiority of LaPIG.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LaPIG: Cross-Modal Generation of Paired Thermal and Visible Facial Images
Wang, Leyang
Lin, Joice
Computer Vision and Pattern Recognition
The success of modern machine learning, particularly in facial translation networks, is highly dependent on the availability of high-quality, paired, large-scale datasets. However, acquiring sufficient data is often challenging and costly. Inspired by the recent success of diffusion models in high-quality image synthesis and advancements in Large Language Models (LLMs), we propose a novel framework called LLM-assisted Paired Image Generation (LaPIG). This framework enables the construction of comprehensive, high-quality paired visible and thermal images using captions generated by LLMs. Our method encompasses three parts: visible image synthesis with ArcFace embedding, thermal image translation using Latent Diffusion Models (LDMs), and caption generation with LLMs. Our approach not only generates multi-view paired visible and thermal images to increase data diversity but also produces high-quality paired data while maintaining their identity information. We evaluate our method on public datasets by comparing it with existing methods, demonstrating the superiority of LaPIG.
title LaPIG: Cross-Modal Generation of Paired Thermal and Visible Facial Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16376