Generating Clear Images From Images With Distortions Caused by Adverse Weather Using Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based method to remove weather-induced distortions from images, significantly improving computer vision tasks like object recognition crucial for autonomous vehicles.

Contribution

We developed a generative adversarial network that effectively removes raindrop distortions, enhancing image clarity for autonomous driving applications.

Findings

Object recognition performance is restored after de-raining.

GAN effectively removes raindrop distortions from images.

Method applicable to various adverse weather conditions.

Abstract

We presented a method for improving computer vision tasks on images affected by adverse weather conditions, including distortions caused by adherent raindrops. Overcoming the challenge of applying computer vision to images affected by adverse weather conditions is essential for autonomous vehicles utilizing RGB cameras. For this purpose, we trained an appropriate generative adversarial network and showed that it was effective at removing the effect of the distortions, in the context of image reconstruction and computer vision tasks. We showed that object recognition, a vital task for autonomous driving vehicles, is completely impaired by the distortions and occlusions caused by adherent raindrops and that performance can be restored by our de-raining model. The approach described in this paper could be applied to all adverse weather conditions.