STEREOFOG -- Computational DeFogging via Image-to-Image Translation on a real-world Dataset

Abstract

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.

7 pages, 7 figures, for associated dataset and Supplement file, see https://github.com/apoll2000/stereofog

References in corpus (6)

• MixDehazeNet : Mix Structure Block For Image Dehazing Network
• Imaging through fog using quadrature lock-in discrimination
• Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal
• Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval
• Quantum defogging: temporal photon number fluctuation correlation in time-variant fog scattering medium
• High Resolution Millimeter Wave Imaging Based on FMCW Radar Systems at W-Band