DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911101209280512 |
|---|---|
| author | Ma, Wenzhuo Chen, Zhenzhong |
| author_facet | Ma, Wenzhuo Chen, Zhenzhong |
| contents | In this work, we first propose DiffVC-OSD, a One-Step Diffusion-based Perceptual Neural Video Compression framework. Unlike conventional multi-step diffusion-based methods, DiffVC-OSD feeds the reconstructed latent representation directly into a One-Step Diffusion Model, enhancing perceptual quality through a single diffusion step guided by both temporal context and the latent itself. To better leverage temporal dependencies, we design a Temporal Context Adapter that encodes conditional inputs into multi-level features, offering more fine-grained guidance for the Denoising Unet. Additionally, we employ an End-to-End Finetuning strategy to improve overall compression performance. Extensive experiments demonstrate that DiffVC-OSD achieves state-of-the-art perceptual compression performance, offers about 20$\times$ faster decoding and a 86.92\% bitrate reduction compared to the corresponding multi-step diffusion-based variant. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework Ma, Wenzhuo Chen, Zhenzhong Image and Video Processing Computer Vision and Pattern Recognition In this work, we first propose DiffVC-OSD, a One-Step Diffusion-based Perceptual Neural Video Compression framework. Unlike conventional multi-step diffusion-based methods, DiffVC-OSD feeds the reconstructed latent representation directly into a One-Step Diffusion Model, enhancing perceptual quality through a single diffusion step guided by both temporal context and the latent itself. To better leverage temporal dependencies, we design a Temporal Context Adapter that encodes conditional inputs into multi-level features, offering more fine-grained guidance for the Denoising Unet. Additionally, we employ an End-to-End Finetuning strategy to improve overall compression performance. Extensive experiments demonstrate that DiffVC-OSD achieves state-of-the-art perceptual compression performance, offers about 20$\times$ faster decoding and a 86.92\% bitrate reduction compared to the corresponding multi-step diffusion-based variant. |
| title | DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.07682 |