.png){kind=icon}
返回
Event-Aware Video Deraining via Multi-Patch Progressive Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2023.3272283.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we address the problem of video-based rain streak removal by developing an event-aware multi-patch progressive neural network. Rain streaks in video exhibit correlations in both temporal and spatial dimensions. Existing methods have difficulties in modeling the characteristics. Based on the observation, we propose to develop a module encoding events from neuromorphic cameras to facilitate deraining. Events are captured asynchronously at pixel-level only when intensity changes by a margin exceeding a certain threshold. Due to this property, events contain considerable information about moving objects including rain streaks passing though the camera across adjacent frames. Thus we suggest that utilizing it properly facilitates deraining performance non-trivially. In addition, we develop a multi-patch progressive neural network. The multi-patch manner enables various receptive fields by partitioning patches and the progressive learning in different patch levels makes the model emphasize each patch level to a different extent. Extensive experiments show that our method guided by events outperforms the state-of-the-art methods by a large margin in synthetic and real-world datasets.
Keyword:
Rain
Cameras
Convolutional neural networks
Task analysis
Neural networks
Correlation
Sun
Video deraining
event-aware
progressive learning
multi-patch learning
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
Why House Wrens Destroy Clutches of Other Birds: A Support for the Nest Site Competition Hypothesis.png)
The Condor
The CondorIF0
PREAI
分享收藏The influence of stacking fault energy and adhesion on the wear of copper and aluminum bronzeWear
WearIF0
PREAI
分享收藏Crystalline‐State Reaction with Allosteric Effect in Spin‐Crossover, Interpenetrated Networks with Magnetic and Optical Bistability具有磁和光学双稳态的自旋交叉，互穿网络中具有变构效应的晶态反应
PREAI
分享收藏分享收藏分享收藏
查看更多内容