Temporally consistent low-light face video enhancement via video-to-video conditional diffusion

Abstract Low-light face videos suffer from severe noise and detail loss, limiting their use in surveillance and photography applications. To address these challenges, this paper proposes DL-Diff, a novel low-light face video enhancement framework that formulates this task as a conditional video-to-v...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Xiaofeng Ding, Kailin He, Huo Sun, Juying Yang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Nature Portfolio 2026-03-01
coleção:	Scientific Reports
Assuntos:	Low-light face video enhancement (LLFVE) Latent diffusion models (LDMs) Video-to-video generation (V2V) Temporal consistency Pre-trained models
Acesso em linha:	https://doi.org/10.1038/s41598-026-44219-8
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!