US 11,928,779 B2
Multi-resolution voxel meshing
Maxime Meilland, Nice (FR); Andrew Predoehl, Mountain View, CA (US); Kyle L. Simek, San Jose, CA (US); Ming Chuang, Mountain View, CA (US); and Pedro A. Pinies Rodriguez, San Jose, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Apr. 11, 2022, as Appl. No. 17/717,393.
Application 17/717,393 is a continuation of application No. 17/147,559, filed on Jan. 13, 2021, granted, now 11,328,481.
Claims priority of provisional application 62/962,481, filed on Jan. 17, 2020.
Prior Publication US 2022/0237872 A1, Jul. 28, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 17/20 (2006.01)
CPC G06T 17/20 (2013.01) [G06T 3/4007 (2013.01); G06T 2200/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
at an electronic device having a processor and a sensor:
obtaining depth data of a physical environment using the sensor at a sensor position, the physical environment comprising surfaces;
determining, based on the depth data and determined distances to the surfaces of the physical environment, a plurality of resolutions associated with the obtained depth data;
determining, based on the determined plurality of resolutions, multi-resolution voxels that include at least a first set of voxels that comprises a first resolution and a second set of voxels that comprises a second resolution that is different than the first resolution based on the first set of voxels being positioned at distances within a first distance range of the sensor position and the second set of voxels being positioned at distances within a second distance range of the sensor position; and
generating a single mesh of different resolutions by positioning vertices along a line connecting a first voxel of the first set of voxels corresponding to the first resolution with a second voxel of the second set of voxels corresponding to the second resolution, wherein the single mesh is generated directly from the multi-resolution voxels.