US 12,231,674 B2
Systems and methods for encoding an image
Philippe Martin Burlina, Rockville, MD (US); and Subhasis Das, San Mateo, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Jan. 26, 2023, as Appl. No. 18/101,851.
Prior Publication US 2024/0259585 A1, Aug. 1, 2024
Int. Cl. H04N 19/52 (2014.01); G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 20/56 (2022.01)
CPC H04N 19/52 (2014.11) [G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/7715 (2022.01); G06V 20/56 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computer executable instructions that, when executed by the one or more processors, cause the system to perform actions comprising:
receiving, from a camera of a vehicle, an input image;
determining, based at least in part on the input image, a set of patches of the input image;
determining, based at least in part on the set of patches, a subset of patches from the set of patches, the subset of patches determined based at least in part on a respective level of importance of the patches of the subset of patches to cause control of an autonomous vehicle;
determining, by an encoder machine-learned (ML) model and based at least in part on the subset of patches, a set of encoding vectors associated with the subset of patches;
determining, by a decoder ML model and based at least in part on the set of encoding vectors, a reconstructed image;
comparing the reconstructed image with the input image;
determining, based at least in part on the comparing, a difference dataset between the reconstructed image and the input image;
determining first data based at least in part on the set of encoding vectors;
determining second data based at least in part on the difference dataset; and
transmitting the first data and the second data for the input image to be reconstructed.