[TPAMI-2023] Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better

论文阅读 [TPAMI-2023] Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better

论文搜索(studyai.com)

搜索论文: Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better

搜索论文: http://www.studyai.com/search/whole-site/?q=Enhanced+Spatio-Temporal+Interaction+Learning+for+Video+Deraining:+Faster+and+Better&fr=csdn

关键字(Keywords)

Feature extraction; Rain; Computer architecture; Logic gates; Correlation; Data mining; Image restoration; Video deraining; spatio-temporal learning; faster and better; ESTINet

机器学习; 机器视觉

递归神经网络; 时间与空间; 图像/视频去雨痕

摘要(Abstract)

Video deraining is an important task in computer vision as the unwanted rain hampers the visibility of videos and deteriorates the robustness of most outdoor vision systems.

视频去噪是计算机视觉中的一项重要任务，因为多余的雨水会阻碍视频的可见性，并使大多数户外视觉系统的鲁棒性下降。

Despite the significant success which has been achieved for video deraining recently, two major challenges remain: 1) how to exploit the vast information among successive frames to extract powerful spatio-temporal features across both the spatial and temporal domains, and 2) how to restore high-quality derained videos with a high-speed approach.

尽管最近在视频去噪方面取得了重大成功，但仍存在两个主要挑战：1）如何利用连续帧之间的大量信息，以跨空间和时间域提取强大的时空特征，以及2）如何使用高速方法恢复高质量去噪视频。

In this paper, we present a new end-to-end video deraining framework, dubbed Enhanced Spatio-Temporal Interaction Network (ESTINet), which considerably boosts current state-of-the-art video deraining quality and speed.

在本文中，我们提出了一种新的端到端视频降级框架，称为增强时空交互网络（ESTINet），它大大提高了当前最先进的视频降级质量和速度。

The ESTINet takes the advantage of deep residual networks and convolutional long short-term memory, which can capture the spatial features and temporal correlations among successive frames at the cost of very little computational resource.

ESTINet利用了深度残差网络和卷积长短期存储器的优势，可以以很少的计算资源为代价捕获连续帧之间的空间特征和时间相关性。

Extensive experiments on three public datasets show that the proposed ESTINet can achieve faster speed than the competitors, while maintaining superior performance over the state-of-the-art methods.

在三个公共数据集上的大量实验表明，所提出的ESTINet可以实现比竞争对手更快的速度，同时保持优于最先进方法的性能。

https://github.com/HDCVLab/Enhanced-Spatio-Temporal-Interaction-Learning-for-Video-Deraining…

https://github.com/HDCVLab/Enhanced-Spatio-Temporal-Interaction-Learning-for-Video-Deraining.。

作者(Authors)

[‘Kaihao Zhang’, ‘Dongxu Li’, ‘Wenhan Luo’, ‘Wenqi Ren’, ‘Wei Liu’]