Abstract: A system may be configured for implementing neural volumetric reconstruction for coherent synthetic aperture sonar. Exemplary systems include means for measuring underwater objects using high-resolution Synthetic aperture sonar (SAS) by coherently combining data from a moving array to form high-resolution imagery. Such a system may receive a waveform from the measurements of the underwater object and optimize the waveform for deconvolving via an iterative deconvolution optimization process applying an adaptable approach to waveform compression where performance is tuned via sparsity and smoothness parameters. Such a system may deconvolve the wave form using pulse deconvolution and use the deconvolved waveforms in an analysis-by-synthesis optimization operation with an implicit neural representation to yield higher resolution and superior volumetric reconstruction scene of the underwater object.

Abstract: In some implementations, there is provided a computer-implemented method comprising sampling a set of coordinates describing a volume in which an object is positioned, acquiring a plurality of true radar measurements describing a position of the object in the volume, encoding the set of coordinates to yield plurality of encoded coordinates, predicting, based on the plurality of encoded coordinates and using a machine learning model, a scattering function for the object in the volume; and generating, based on the scattering function for the object, a plurality of estimated radar measurements describing the position of the object. In some implementations, the method comprises training the machine learning model to minimize a difference between the plurality of estimated radar measurements and the plurality of true radar measurements.

Abstract: A system may be configured for implementing neural volumetric reconstruction for coherent synthetic aperture sonar. Exemplary systems include means for measuring underwater objects using high-resolution Synthetic aperture sonar (SAS) by coherently combining data from a moving array to form high-resolution imagery. Such a system may receive a waveform from the measurements of the underwater object and optimize the waveform for deconvolving via an iterative deconvolution optimization process applying an adaptable approach to waveform compression where performance is tuned via sparsity and smoothness parameters. Such a system may deconvolve the wave form using pulse deconvolution and use the deconvolved waveforms in an analysis-by-synthesis optimization operation with an implicit neural representation to yield higher resolution and superior volumetric reconstruction scene of the underwater object.