Generating Clear Images From Images With Distortions Caused by Adverse Weather Using Generative Adversarial Networks
This addresses a critical safety issue for autonomous vehicles using RGB cameras, though it appears incremental as it applies existing GAN methods to a specific weather-related challenge.
The paper tackles the problem of computer vision impairment in autonomous vehicles due to adverse weather distortions like raindrops, by using a generative adversarial network to remove these distortions and restore object recognition performance.
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.