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...
Guardat en:
| Autors principals: | , , , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
Nature Portfolio
2026-03-01
|
| Col·lecció: | Scientific Reports |
| Matèries: | |
| Accés en línia: | https://doi.org/10.1038/s41598-026-44219-8 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|