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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The rapid development of deep learning provides a better solution for theend-to-end reconstruction of hyperspectral image (HSI). However, existinglearning-based methods have two major defects. Firstly, networks withself-attention usually sacrifice internal resolution to balance modelperformance against complexity, losing fine-grained high-resolution (HR)features. Secondly, even if the optimization focusing on spatial-spectraldomain learning (SDL) converges to the ideal solution, there is still asignificant visual difference between the reconstructed HSI and the truth.Therefore, we propose a high-resolution dual-domain learning network (HDNet)for HSI reconstruction. On the one hand, the proposed HR spatial-spectralattention module with its efficient feature fusion provides continuous and finepixel-level features. On the other hand, frequency domain learning (FDL) isintroduced for HSI reconstruction to narrow the frequency domain discrepancy.Dynamic FDL supervision forces the model to reconstruct fine-grainedfrequencies and compensate for excessive smoothing and distortion caused bypixel-level losses. The HR pixel-level attention and frequency-level refinementin our HDNet mutually promote HSI perceptual quality. Extensive quantitativeand qualitative evaluation experiments show that our method achieves SOTAperformance on simulated and real HSI datasets. Code and models will bereleased at https://github.com/caiyuanhao1998/MST

HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging