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...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Xiaofeng Ding, Kailin He, Huo Sun, Juying Yang
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Nature Portfolio 2026-03-01
Edice:	Scientific Reports
Témata:	Low-light face video enhancement (LLFVE) Latent diffusion models (LDMs) Video-to-video generation (V2V) Temporal consistency Pre-trained models
On-line přístup:	https://doi.org/10.1038/s41598-026-44219-8
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!