Single image defogging and evaluation with deep neural networks without the need of ground truth

Fog, haze, or smoke are usual atmospheric phenomena that dramatically compromise the overall visibility of any scene, critically affecting features such as illumination, contrast, and contour detection of objects. The decrease in visibility compromises the performance of computer vision algorithms such as pattern recognition and segmentation, some of them very relevant for decision-making in the field of autonomous vehicles. Several dehazing methods have been proposed that either need to estimate fog parameters through physical models or are statistically based. But physical parameters greatly depend on the scene conditions, and statistically based methods require large datasets of natural foggy images together with the original images without fog, i.e. the ground truth, for evaluation. Obtaining proper fog-less ground truth images for pixel-to-pixel evaluation is costly and time-consuming, and this fact hinders progress in the field. This paper aims to tackle this issue by proposing a gradient-based metrics for image defogging evaluation that does not need a ground truth image without fog or a physical model. A comparison of the proposed metrics with metrics already used in the NTIRE 2018 defogging challenge as well as several state-of-the-art defogging evaluation metrics is performed to prove its effectiveness in a general situation, showing comparable results to conventional metrics and an improvement in the no-reference scene. A Matlab implementation of the proposed metrics has been developed and it is open-sourced in a public GitHub repository.This work has been possible thanks to the project PID2020-119484RB-I00 and TED2021-132338B-I00 funded by Ministerio de Ciencia e Innovaci´on de Espa˜na. This work is part of a Ph.D. thesis with grant number 2023 FI-1 00229 co-funded by the European Union.Peer ReviewedPostprint (author's final draft