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 Plus

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

Zendy Tools

Zendy Open

Hyperspectral unmixing is an important remote sensing task with applicationsincluding material identification and analysis. Characteristic spectralfeatures make many pure materials identifiable from their visible-to-infraredspectra, but quantifying their presence within a mixture is a challenging taskdue to nonlinearities and factors of variation. In this paper, spectralvariation is considered from a physics-based approach and incorporated into anend-to-end spectral unmixing algorithm via differentiable programming. Thedispersion model is introduced to simulate realistic spectral variation, and anefficient method to fit the parameters is presented. Then, this dispersionmodel is utilized as a generative model within an analysis-by-synthesisspectral unmixing algorithm. Further, a technique for inverse rendering using aconvolutional neural network to predict parameters of the generative model isintroduced to enhance performance and speed when training data is available.Results achieve state-of-the-art on both infrared and visible-to-near-infrared(VNIR) datasets, and show promise for the synergy between physics-based modelsand deep learning in hyperspectral unmixing in the future.

Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model