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

This paper tackles the challenging problem of hyperspectral (HS) imagedenoising. Unlike existing deep learning-based methods usually adoptingcomplicated network architectures or empirically stacking off-the-shelf modulesto pursue performance improvement, we focus on the efficient and effectivefeature extraction manner for capturing the high-dimensional characteristics ofHS images. To be specific, based on the theoretical analysis that increasingthe rank of the matrix formed by the unfolded convolutional kernels can promotefeature diversity, we propose rank-enhanced low-dimensional convolution set(Re-ConvSet), which separately performs 1-D convolution along the threedimensions of an HS image side-by-side, and then aggregates the resultingspatial-spectral embeddings via a learnable compression layer. Re-ConvSet notonly learns the diverse spatial-spectral features of HS images, but alsoreduces the parameters and complexity of the network. We then incorporateRe-ConvSet into the widely-used U-Net architecture to construct an HS imagedenoising method. Surprisingly, we observe such a concise framework outperformsthe most recent method to a large extent in terms of quantitative metrics,visual results, and efficiency. We believe our work may shed light on deeplearning-based HS image processing and analysis.

Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising