US 12,462,463 B2
Method and apparatus for viewport shifting of non-real time 3D applications
Joanna Douglas, Hillsboro, OR (US); Michal Taryma, Hillsboro, OR (US); Mario Garcia, Hillsboro, OR (US); and Carlos Dominguez, Hillsboro, OR (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Jun. 24, 2024, as Appl. No. 18/751,775.
Application 18/751,775 is a continuation of application No. 17/502,518, filed on Oct. 15, 2021, granted, now 12,039,654.
Application 17/502,518 is a continuation of application No. 16/722,685, filed on Dec. 20, 2019, granted, now 11,200,722, issued on Dec. 14, 2021.
Prior Publication US 2025/0029312 A1, Jan. 23, 2025
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 15/00 (2011.01); G06T 1/20 (2006.01); G06T 3/4053 (2024.01); G06T 15/50 (2011.01)
CPC G06T 15/005 (2013.01) [G06T 1/20 (2013.01); G06T 3/4053 (2013.01); G06T 15/503 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A graphics processing unit, comprising:
memory to store graphics commands; and
a streaming multiprocessor coupled to the memory, the streaming multiprocessor configured to:
generate a first frame based on the graphics commands;
generate a dataset based on the first frame and a plurality of replays of the graphics commands to generate a plurality of second frames having jittered viewpoints of the first frame, the dataset including a plurality of sample positions associated with modified viewpoints of the first frame, wherein the graphics commands include commands to configure a mip level of detail (LOD) for the first frame and the plurality of second frames that corresponds to the mip LOD that corresponds with a resolution of a third frame; and
train a machine learning model based on the dataset to enable generation of the third frame, wherein the third frame is a super sampled and anti-aliased frame having a higher resolution relative to the first frame.