US 12,262,036 B1
System and methods for image series transformation for optimal compressibility with neural upsampling
Brian Galvin, Silverdale, WA (US)
Assigned to ATOMBEAM TECHNOLOGIES INC, Moraga, CA (US)
Filed by AtomBeam Technologies Inc., Moraga, CA (US)
Filed on Oct. 14, 2024, as Appl. No. 18/915,030.
Application 18/915,030 is a continuation in part of application No. 18/668,163, filed on May 18, 2024, granted, now 12,167,031.
Application 18/668,163 is a continuation in part of application No. 18/537,728, filed on Dec. 12, 2023, granted, now 12,058,333, issued on Aug. 6, 2024.
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 19/42 (2014.01); H04N 19/119 (2014.01); H04N 19/132 (2014.01); H04N 19/136 (2014.01); H04N 19/174 (2014.01); H04N 19/60 (2014.01); H04N 19/66 (2014.01)
CPC H04N 19/42 (2014.11) [H04N 19/119 (2014.11); H04N 19/132 (2014.11); H04N 19/136 (2014.11); H04N 19/174 (2014.11); H04N 19/60 (2014.11); H04N 19/66 (2014.11)] 16 Claims
OG exemplary drawing
 
1. A system for image series transformation for optimal compressibility with neural upsampling and error resilience, comprising:
a computing device comprising at least a memory and a processor;
a plurality of programming instructions that, when operating on the processor, cause the computing device to:
collect a plurality of images;
train an angle optimizer using the plurality of images on how to optimally slice the plurality of images to maximize each image's compressibility;
slice the images along an optimal angle, as determined by the angle optimizer; and
reconstruct the slices images into a plurality of reconstructed images;
encode the plurality of reconstructed images into a plurality of compressed images;
apply error resilience techniques to the compressed images;
decode the plurality of compressed images into a plurality of decompressed images; and
upsample the plurality of compressed images using a correlation network, where the output includes more information than the plurality of reconstructed images.