In this paper we present a novel defogging technique,named CurL-Defog, aimed at minimizing the creation of unwanted artifacts during the defogging process. The majority of learning based defogging approaches rely on paired data (i.e.,the same images with and without fog), where fog is artificially added to clear images: this often provides good results on mildly fogged images but does not generalize well to real difficult cases. On the other hand, the models trained with real unpaired data (e.g. CycleGAN) can provide visually impressive results but they often produce unwanted artifacts. In this paper we propose a curriculum learning strategy coupled with an enhanced CycleGAN model in order to reduce the number of produced artifacts, while maintaining state-of-the-art performance in terms of contrast enhancement and image reconstruction. We also introduce a new metric, called HArD (Hazy Artifact Detector) to numerically quantify the amount of artifacts in the defogged images, thus avoiding the tedious and subjective manual inspection of the results. The proposed approach compares favorably with state-of-the-art techniques on both real and synthetic datasets.

Gabriele Graffieti, Davide Maltoni (2021). Towards Artifacts-free Image Defogging. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA : Institute of Electrical and Electronics Engineers Inc. [10.1109/ICPR48806.2021.9412289].

Towards Artifacts-free Image Defogging

Gabriele Graffieti
Primo
;
Davide Maltoni
Secondo
2021

Abstract

In this paper we present a novel defogging technique,named CurL-Defog, aimed at minimizing the creation of unwanted artifacts during the defogging process. The majority of learning based defogging approaches rely on paired data (i.e.,the same images with and without fog), where fog is artificially added to clear images: this often provides good results on mildly fogged images but does not generalize well to real difficult cases. On the other hand, the models trained with real unpaired data (e.g. CycleGAN) can provide visually impressive results but they often produce unwanted artifacts. In this paper we propose a curriculum learning strategy coupled with an enhanced CycleGAN model in order to reduce the number of produced artifacts, while maintaining state-of-the-art performance in terms of contrast enhancement and image reconstruction. We also introduce a new metric, called HArD (Hazy Artifact Detector) to numerically quantify the amount of artifacts in the defogged images, thus avoiding the tedious and subjective manual inspection of the results. The proposed approach compares favorably with state-of-the-art techniques on both real and synthetic datasets.
2021
2020 25th International Conference on Pattern Recognition (ICPR)
5060
5067
Gabriele Graffieti, Davide Maltoni (2021). Towards Artifacts-free Image Defogging. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA : Institute of Electrical and Electronics Engineers Inc. [10.1109/ICPR48806.2021.9412289].
Gabriele Graffieti; Davide Maltoni
File in questo prodotto:
File Dimensione Formato  
Towards_Artifacts-Free_Image_Defogging.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 7.52 MB
Formato Adobe PDF
7.52 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/794739
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact