Please use this identifier to cite or link to this item:
http://dspace.bits-pilani.ac.in:8080/jspui/xmlui/handle/123456789/8351
Title: | HIDeGan: A Hyperspectral-guided Image Dehazing GAN |
Authors: | Narang, Pratik |
Keywords: | Computer Science Dehazing GAN Image reconstruction Hyperspectral imaging Gallium nitride Atmospheric modeling |
Issue Date: | 2020 |
Publisher: | IEEE |
Abstract: | Haze removal in images captured from a diverse set of scenarios is a very challenging problem. The existing dehazing methods either reconstruct the transmission map or directly estimate the dehazed image in RGB color space. In this paper, we make a first attempt to propose a Hyperspectral-guided Image Dehazing Generative Adversarial Network (HIDEGAN). The HIDEGAN architecture is formulated by designing an enhanced version of CYCLEGAN named R2HCYCLE and an enhanced conditional GAN named H2RGAN. The R2HCYCLE makes use of the hyperspectral-image (HSI) in combination with cycle-consistency and skeleton losses in order to improve the quality of information recovery by analyzing the entire spectrum. The H2RGAN estimates the clean RGB image from the hazy hyperspectral image generated by the R2HCYCLE. The models designed for spatial-spectral-spatial mapping generate visually better haze-free images. To facilitate HSI generation, datasets from spectral reconstruction challenge at NTIRE 2018 and NTIRE 2020 are used. A comprehensive set of experiments were conducted on the D-Hazy, and the recent RESIDE-Standard (SOTS), RESIDE-β (OTS) and RESIDE-Standard (HSTS) datasets. The proposed HIDEGAN outperforms the existing state-of-the-art in all these datasets. |
URI: | https://ieeexplore.ieee.org/document/9150802 http://dspace.bits-pilani.ac.in:8080/xmlui/handle/123456789/8351 |
Appears in Collections: | Department of Computer Science and Information Systems |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.