IP Library › Granted Patent US 12670543
Granted Patent B2
US 12670543 · App. 18/106,963 · Granted Jun 30, 2026

Method and system to implement application programming interface (API) indicating frame interpolation support for interpolating video frames

Inventors: Robert Thomas Pottorff (Layton, UT); Karan Sapra (San Jose, CA); Andrew Leighton Edelsten (Morgan Hill, CA)
Assignee: NVIDIA Corporation
G06T3/4046G06T1/20G06T3/4007G06N3/02G06V10/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12670543
App. No.
18/106,963
Granted
Jun 30, 2026
Kind
B2
Abstract

Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to indicate support to use one or more neural networks to perform frame interpolation.

Claims (34)

1 . A processor, comprising:

one or more circuits to implement an application programming interface (API) for frame interpolation, the one or more circuits to:

determine, responsive to a first API call indicating a frame interpolation feature, whether a computing environment includes capabilities to perform the indicated frame interpolation feature using one or more neural networks;

provide, based on determination that the computing environment includes the capabilities, a return result of the API call indicating the computing environment includes the capabilities to perform the indicated frame interpolation feature;

cause, responsive to a second API call, the indicated frame interpolation feature interpretation to be performed for a plurality of rendered frames using the one or more neural networks to generate one or more blending factors; and

generate one or more interpolated frames based, at least in part, on the one or more blending factors and the plurality of rendered frames.

2 . The processor of claim 1 , wherein the API is to receive one or more input values indicating a feature to use the one or more neural networks to perform the frame interpolation.

3 . The processor of claim 1 , wherein the API is to receive one or more input values indicating one or more graphics processing units (GPUs) of which the support is to be indicated.

4 . The processor of claim 1 , wherein the API is to receive one or more input values indicating a storage location to store a determination of the support to perform the frame interpolation.

5 . The processor of claim 1 , wherein the API is to determine the support to perform the frame interpolation based, at least in part, on a hardware version of a GPU.

6 . The processor of claim 1 , wherein the API is to determine the support to perform the frame interpolation based, at least in part, on a driver version of a GPU.

7 . The processor of claim 1 , wherein the API is to determine the support to perform the frame interpolation based, at least in part, on a software version of software to be performed by the processor.

8 . A computer-implemented method to implement an application programming interface (API) for frame interpolation, comprising:

determining, responsive to a first application programming interface (API) call indicating a frame interpolation feature, whether a computing environment includes capabilities to perform the indicated frame interpolation feature using one or more neural networks;

providing, based on determination that the computing environment includes the capabilities, a return result of the API call indicating the computing environment includes the capabilities to perform the indicated frame interpolation feature;

causing, responsive to a second API call, the indicated frame interpolation feature interpretation to be performed for a plurality of rendered frames using the one or more neural networks to generate one or more blending factors; and

generating one or more interpolated frames based, at least in part, on the one or more blending factors and the plurality of rendered frames.

9 . The computer-implemented method of claim 8 , wherein the API is to receive one or more input values indicating a feature to use the one or more neural networks to perform the frame interpolation.

10 . The computer-implemented method of claim 8 , wherein the API is to receive one or more input values indicating one or more processors of which the support is to be indicated.

11 . The computer-implemented method of claim 8 , wherein the API is to receive one or more input values indicating a storage location to store a determination of the support to perform the frame interpolation.

12 . The computer-implemented method of claim 8 , wherein the API is to determine the support to use the one or more neural networks to perform the frame interpolation based, at least in part, on a hardware version of a processor.

13 . The computer-implemented method of claim 8 , wherein the API is to determine the support to perform the frame interpolation based, at least in part, on a driver version of a driver of a processor.

14 . The computer-implemented method of claim 8 , wherein the API is to determine the support to perform the frame interpolation based, at least in part, on a software version of software to be performed by a processor.

15 . A computer system, comprising:

one or more processors and memory storing executable instructions to implement an application programming interface (API) for frame interpolation, wherein the executable instruction, if performed by the one or more processors,

determine, responsive to a first API call indicating a frame interpolation feature, whether a computing environment includes capabilities to perform the indicated frame interpolation feature using one or more neural networks;

provide, based on determination that the computing environment includes the capabilities, a return result of the API call indicating the computing environment includes the capabilities to perform the indicated frame interpolation feature;

cause, responsive to a second API call, the indicated frame interpolation feature interpretation to be performed for a plurality of rendered frames using the one or more neural networks to generate one or more blending factors; and

generate one or more interpolated frames based, at least in part, on the one or more blending factors and the plurality of rendered frames.

16 . The computer system of claim 15 , wherein the API is to receive one or more input values indicating a feature to use the one or more neural networks to perform the frame interpolation.

17 . The computer system of claim 15 , wherein the API is to receive one or more input values indicating one or more graphics processing units (GPUs) of which the support is to be indicated.

18 . The computer system of claim 15 , wherein the API is to receive one or more input values indicating a storage location to store a determination of the support to perform the frame interpolation.

19 . The computer system of claim 15 , wherein the API is to determine the support to perform the frame interpolation based, at least in part, on one or more hardware versions of one or more GPUs.

20 . The computer system of claim 15 , wherein the API is to determine the support to perform the frame interpolation based, at least in part, on one or more driver versions of one or more GPU.