Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation

TL;DR

This paper introduces ViWS-Net, a novel video restoration framework that effectively removes all adverse weather effects from videos by leveraging a weather-agnostic transformer encoder, temporal modeling, and adversarial training.

Contribution

The work presents the first comprehensive framework for restoring videos under all adverse weather conditions using a transformer-based architecture with adversarial learning.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively removes diverse adverse weather effects from videos.

Maintains weather-invariant features while suppressing weather-specific noise.

Abstract

Although convolutional neural networks (CNNs) have been proposed to remove adverse weather conditions in single images using a single set of pre-trained weights, they fail to restore weather videos due to the absence of temporal information. Furthermore, existing methods for removing adverse weather conditions (e.g., rain, fog, and snow) from videos can only handle one type of adverse weather. In this work, we propose the first framework for restoring videos from all adverse weather conditions by developing a video adverse-weather-component suppression network (ViWS-Net). To achieve this, we first devise a weather-agnostic video transformer encoder with multiple transformer stages. Moreover, we design a long short-term temporal modeling mechanism for weather messenger to early fuse input adjacent video frames and learn weather-specific information. We further introduce a weather discriminator with gradient reversion, to maintain the weather-invariant common information and suppress the weather-specific information in pixel features, by adversarially predicting weather types. Finally, we develop a messenger-driven video transformer decoder to retrieve the residual weather-specific feature, which is spatiotemporally aggregated with hierarchical pixel features and refined to predict the clean target frame of input videos. Experimental results, on benchmark datasets and real-world weather videos, demonstrate that our ViWS-Net outperforms current state-of-the-art methods in terms of restoring videos degraded by any weather condition.