← Back to all news
arXiv Computer Vision By Kui Jiang, Yiang Chen, Yan Luo, Zhaocheng Yu, Junjun Jiang, Xianming Liu

S3VD: Semantic-Guidance Spatio-Temporal Scanning for Video Deraining

Read the original on arXiv Computer Vision →

S3VD is a new video deraining framework that leverages semantic guidance and spatio‑temporal scanning to improve performance over existing State Space Models such as Mamba. It introduces a Multi‑Scale Semantic Fusion module that uses DINOv2 priors to preserve 2D spatial semantics, and a Spatio‑Temporal Scanning Fusion module that incorporates a Decoupled‑Gating Mamba layer to better model intra‑ and inter‑frame correlations. Experiments on video deraining benchmarks show that S3VD achieves state‑of‑the‑art results, improving PSNR by an average of 0.84 dB over Mamba‑based baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 25

FluidRain: Incompressible Rain Flow as an Attention Bias for Loop-in-Loop Video Deraining

FluidRain is a lightweight video deraining model that leverages a divergence‑free rain flow field to guide Loop‑in‑Loop attention across scales and neighboring frames, eliminating the need for explicit motion alignment. By projecting estimated rain‑flow onto a divergence‑free subspace, the method steers window attention along rain streaks, enabling efficient temporal aggregation with only 0.80 M parameters. Experiments on four benchmarks demonstrate competitive performance against larger models, and the authors introduce a new RainSyn‑Gust dataset and a physics‑based no‑reference metric for evaluating real‑rain removal.

By Pu Wang, Yongcong Wang, Wenhao Li, Xiang Chen, Guangwei Gao, Jinshan Pan, Siyuan Yao, Shujun Fu, Zhuoran Zheng
benchmarkssafety
More like this →