LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Haiyu, Shan, Yiwen, Gou, Yuanbiao, Peng, Xi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908719967633408
author Zhao, Haiyu
Shan, Yiwen
Gou, Yuanbiao
Peng, Xi
author_facet Zhao, Haiyu
Shan, Yiwen
Gou, Yuanbiao
Peng, Xi
contents Recent studies have explored all-in-one video restoration, which handles multiple degradations with a unified model. However, these approaches still face two challenges when dealing with time-varying degradations. First, the degradation can dominate temporal modeling, confusing the model to focus on artifacts rather than the video content. Second, current methods typically rely on large models to handle all-in-one restoration, concealing those underlying difficulties. To address these challenges, we propose a lightweight all-in-one video restoration network, LaverNet, with only 362K parameters. To mitigate the impact of degradations on temporal modeling, we introduce a novel propagation mechanism that selectively transmits only degradation-agnostic features across frames. Through LaverNet, we demonstrate that strong all-in-one restoration can be achieved with a compact network. Despite its small size, less than 1\% of the parameters of existing models, LaverNet achieves comparable, even superior performance across benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation
Zhao, Haiyu
Shan, Yiwen
Gou, Yuanbiao
Peng, Xi
Computer Vision and Pattern Recognition
Recent studies have explored all-in-one video restoration, which handles multiple degradations with a unified model. However, these approaches still face two challenges when dealing with time-varying degradations. First, the degradation can dominate temporal modeling, confusing the model to focus on artifacts rather than the video content. Second, current methods typically rely on large models to handle all-in-one restoration, concealing those underlying difficulties. To address these challenges, we propose a lightweight all-in-one video restoration network, LaverNet, with only 362K parameters. To mitigate the impact of degradations on temporal modeling, we introduce a novel propagation mechanism that selectively transmits only degradation-agnostic features across frames. Through LaverNet, we demonstrate that strong all-in-one restoration can be achieved with a compact network. Despite its small size, less than 1\% of the parameters of existing models, LaverNet achieves comparable, even superior performance across benchmarks.
title LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16313