STEREOFOG -- Computational DeFogging via Image-to-Image Translation on a real-world Dataset
This addresses the challenge of adverse weather conditions for autonomous vehicles by providing a novel dataset and method, though it is incremental as it applies an existing framework to new data.
The authors tackled the problem of removing fog from images for applications like autonomous vehicles by introducing STEREOFOG, a real-world dataset of 10,067 paired fogged and clear images, and applying the pix2pix framework to achieve an average CW-SSIM score of 0.76, demonstrating the technique's suitability.
Image-to-Image translation (I2I) is a subtype of Machine Learning (ML) that has tremendous potential in applications where two domains of images and the need for translation between the two exist, such as the removal of fog. For example, this could be useful for autonomous vehicles, which currently struggle with adverse weather conditions like fog. However, datasets for I2I tasks are not abundant and typically hard to acquire. Here, we introduce STEREOFOG, a dataset comprised of $10,067$ paired fogged and clear images, captured using a custom-built device, with the purpose of exploring I2I's potential in this domain. It is the only real-world dataset of this kind to the best of our knowledge. Furthermore, we apply and optimize the pix2pix I2I ML framework to this dataset. With the final model achieving an average Complex Wavelet-Structural Similarity (CW-SSIM) score of $0.76$, we prove the technique's suitability for the problem.