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/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Color plays an important role in human visual perception, reflecting thespectrum of objects. However, the existing infrared and visible image fusionmethods rarely explore how to handle multi-spectral/channel data directly andachieve high color fidelity. This paper addresses the above issue by proposinga novel method with diffusion models, termed as Dif-Fusion, to generate thedistribution of the multi-channel input data, which increases the ability ofmulti-source information aggregation and the fidelity of colors. In specific,instead of converting multi-channel images into single-channel data in existingfusion methods, we create the multi-channel data distribution with a denoisingnetwork in a latent space with forward and reverse diffusion process. Then, weuse the the denoising network to extract the multi-channel diffusion featureswith both visible and infrared information. Finally, we feed the multi-channeldiffusion features to the multi-channel fusion module to directly generate thethree-channel fused image. To retain the texture and intensity information, wepropose multi-channel gradient loss and intensity loss. Along with the currentevaluation metrics for measuring texture and intensity fidelity, we introduce anew evaluation metric to quantify color fidelity. Extensive experimentsindicate that our method is more effective than other state-of-the-art imagefusion methods, especially in color fidelity.

Dif-Fusion: Towards High Color Fidelity in Infrared and Visible Image Fusion with Diffusion Models