English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

In many real world scenarios, it is difficult to capture the images in thevisible light spectrum (VIS) due to bad lighting conditions. However, theimages can be captured in such scenarios using Near-Infrared (NIR) and Thermal(THM) cameras. The NIR and THM images contain the limited details. Thus, thereis a need to transform the images from THM/NIR to VIS for better understanding.However, it is non-trivial task due to the large domain discrepancies and lackof abundant datasets. Nowadays, Generative Adversarial Network (GAN) is able totransform the images from one domain to another domain. Most of the availableGAN based methods use the combination of the adversarial and the pixel-wiselosses (like $L_1$ or $L_2$) as the objective function for training. Thequality of transformed images in case of THM/NIR to VIS transformation is stillnot up to the mark using such objective function. Thus, better objectivefunctions are needed to improve the quality, fine details and realism of thetransformed images. A new model for THM/NIR to VIS image transformation calledPerceptual Cyclic-Synthesized Generative Adversarial Network (PCSGAN) isintroduced to address these issues. The PCSGAN uses the combination of theperceptual (i.e., feature based) losses along with the pixel-wise and theadversarial losses. Both the quantitative and qualitative measures are used tojudge the performance of the PCSGAN model over the WHU-IIP face and the RGB-NIRscene datasets. The proposed PCSGAN outperforms the state-of-the-art imagetransformation models, including Pix2pix, DualGAN, CycleGAN, PS2GAN, and PAN interms of the SSIM, MSE, PSNR and LPIPS evaluation measures. The code isavailable at https://github.com/KishanKancharagunta/PCSGAN.

PCSGAN: Perceptual Cyclic-Synthesized Generative Adversarial Networks for Thermal and NIR to Visible Image Transformation