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...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	Xiaofeng Ding, Kailin He, Huo Sun, Juying Yang
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	Nature Portfolio 2026-03-01
Serie:	Scientific Reports
Ämnen:	Low-light face video enhancement (LLFVE) Latent diffusion models (LDMs) Video-to-video generation (V2V) Temporal consistency Pre-trained models
Länkar:	https://doi.org/10.1038/s41598-026-44219-8
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!