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

Synthetic aperture sonar (SAS) image resolution is constrained by waveformbandwidth and array geometry. Specifically, the waveform bandwidth determines apoint spread function (PSF) that blurs the locations of point scatterers in thescene. In theory, deconvolving the reconstructed SAS image with the scene PSFrestores the original distribution of scatterers and yields sharperreconstructions. However, deconvolution is an ill-posed operation that ishighly sensitive to noise. In this work, we leverage implicit neuralrepresentations (INRs), shown to be strong priors for the natural image space,to deconvolve SAS images. Importantly, our method does not require trainingdata, as we perform our deconvolution through an analysis-bysynthesisoptimization in a self-supervised fashion. We validate our method on simulatedSAS data created with a point scattering model and real data captured with anin-air circular SAS. This work is an important first step towards applyingneural networks for SAS image deconvolution.

Implicit Neural Representations for Deconvolving SAS Images