Learning A Rain-Invariant Network For Instance Segmentation In The Rain

Existing normal instance segmentation networks have achieved promising performance in clean scenarios. However, these methods often fail to work well in rainy environments as the appearance of rain causes some important and detailed content to be missing. To solve this challenge, we propose an instance segmentation method in the rain, containing three key elements: pixel enhancement module, feature aggregation block, and rain adaptive learning. These components effectively reduce rain degradation both pixel-level and feature-level, enabling the model to adaptively learn rain-invariant features and extract rich multi-scale context information. Furthermore, to mitigate the scarcity of annotated rainy image instance segmentation datasets, we specially generate a realistic rainy dataset based on a widely used rain synthetic pipeline. Experimental results show that the proposed method obviously outperforms existing state-of-the-art algorithms on rainy scenes, while improving the performance in clear weather.