IP Library Granted Patent US 12,439,118
Granted Patent B1
US 12,439,118 · App. 18/334,040 · Granted Oct 7, 2025

Virtual asset insertion

Inventors: Maxim Arap (San Jose, CA); Chun-Hao Liu (Fremont, CA); Sheng Liu (Redmond, WA)
Assignee: Amazon Technologies, Inc.
H04N21/44008H04N21/2187H04N21/23418H04N21/4312H04N21/8146G06T2207/10016
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 12,439,118
App. No.
18/334,040
Granted
Oct 7, 2025
Kind
B1
Abstract

At least part of a visual pattern may be detected, in an image of a video, at a location within the image. An occlusion determination may be performed corresponding to the at least part of the visual pattern. At least part of a virtual asset may be inserted, based at least in part on the occlusion determination, into the image at the location. An appearance of the at least part of the virtual asset within the image may be adjusted based at least in part on an appearance of the at least part of the visual pattern within the image.

Claims (36)

1. A computing system comprising:

one or more processors; and

one or more memories having stored therein instructions that, upon execution by the one or more processors, cause the computing system to perform computing operations comprising:

detecting, in an image of a video, at least part of a visual pattern at a location within the image, wherein the at least part of the visual pattern is displayed in a scene captured by a camera when generating the image;

determining a difference in color between the at least part of the visual pattern in the image and a corresponding physical representation of the visual pattern inserted into a scene from which the image was captured;

performing a determination that a portion of the visual pattern is occluded in the image;

inserting, based at least in part on the determination, at least part of a virtual asset into the image at the location, wherein the at least part of the virtual asset replaces the at least part of the visual pattern within the image; and

adjusting, based at least in part on the difference in color, a coloration of the at least part of the virtual asset within the image.

2. The computing system of claim 1 , wherein the visual pattern is a checkerboard pattern.

3. The computing system of claim 1 , further comprising adjusting, based at least in part on a blurriness of the at least part of the visual pattern within the image, a blurriness of the at least part of the virtual asset within the image.

4. The computing system of claim 1 , wherein the detecting, the determining, the performing, the inserting and the adjusting are performed in real-time in association with delivery of live streaming video.

5. A computer-implemented method comprising:

detecting, in an image of a video, at least part of a visual pattern at a location within the image;

determining a difference in color between the at least part of the visual pattern in the image and a corresponding physical representation of the visual pattern inserted into a scene from which the image was captured;

performing a determination that a portion of the visual pattern is occluded in the image;

inserting, based at least in part on the determination, at least part of a virtual asset into the image at the location; and

adjusting, based at least in part on the difference in color a, a coloration of the at least part of the virtual asset within the image.

6. The computer-implemented method of claim 5 , wherein the visual pattern is a checkerboard pattern.

7. The computer-implemented method of claim 5 , wherein the visual pattern includes at least black and white.

8. The computer-implemented method of claim 7 , wherein the visual pattern includes at least one additional color in addition to the black and the white.

9. The computer-implemented method of claim 5 , wherein the virtual asset is two-dimensional.

10. The computer-implemented method of claim 5 , wherein the virtual asset is three-dimensional.

11. The computer-implemented method of claim 5 , further comprising: adjusting, based at least in part on a blurriness of the at least part of the visual pattern within the image, a blurriness of the at least part of the virtual asset within the image.

12. The computer-implemented method of claim 5 , further comprising: adjusting, based at least in part on at least one of shadow characteristics or lighting characteristics associated with the at least part of the visual pattern within the image, an appearance of the at least part of the virtual asset within the image.

13. The computer-implemented method of claim 5 , wherein the inserting, based at least in part on the determination, the at least part of the virtual asset into the image at the location comprises inserting the at least part of the virtual asset into one or more areas of the image at which the visual pattern is not occluded.

14. The computer-implemented method of claim 5 , further comprising modifying at least one of a size or an orientation of the at least part of the virtual asset in association with the inserting of the at least part of a virtual asset into the image.

15. The computer-implemented method of claim 5 , wherein the at least part of the visual pattern is displayed in a scene captured by a camera when generating the image.

16. One or more non-transitory computer-readable storage media having stored thereon computing instructions that, upon execution by one or more computing devices, cause the one or more computing devices to perform computing operations comprising:

detecting, in an image of a video, at least part of a visual pattern at a location within the image;

determining a difference in color between the at least part of the visual pattern in the image and a corresponding physical representation of the visual pattern inserted into a scene from which the image was captured;

performing a determination that a portion of the visual pattern is occluded in the image;

inserting, based at least in part on the determination, at least part of a virtual asset into the image at the location; and

adjusting, based at least in part on the difference in color, a coloration of the at least part of the virtual asset within the image.

17. The one or more non-transitory computer-readable storage media of claim 16 , wherein the visual pattern is a checkerboard pattern.

18. The one or more non-transitory computer-readable storage media of claim 16 , wherein the inserting, based at least in part on the determination, the at least part of the virtual asset into the image at the location comprises inserting the at least part of the virtual asset into one or more areas of the image at which the visual pattern is not occluded.

19. The one or more non-transitory computer-readable storage media of claim 18 , wherein the at least part of the virtual asset is not inserted into one or more other areas of the image at which the visual pattern is occluded.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 13, 2023
From: ARAP, MAXIM; LIU, CHUN-HAO; LIU, SHENG
To: AMAZON TECHNOLOGIES, INC.
Reel/Frame 063938/0407 →
References Cited (49)
US 7249367B2 · Bove, Jr. · 2007 [cited by examiner]
US 7779438B2 · Davies · 2010 [cited by examiner]
US 7979877B2 · Huber · 2011 [cited by examiner]
US 8666818B2 · DeVree · 2014 [cited by examiner]
US 8849945B1 · Desjardins · 2014 [cited by examiner]
US 8885217B2 · Ohmiya · 2014 [cited by examiner]
US 9621953B1 · Holcomb · 2017 [cited by examiner]
US 10088983B1 · Qaddoura · 2018 [cited by examiner]
US 10423241B1 · Pham · 2019 [cited by examiner]
US 11017611B1 · Mount · 2021 [cited by examiner]
US 11856261B1 · Stankovska · 2023 [cited by examiner]
US 12228790B2 · Fukuda · 2025 [cited by examiner]
US 20020059588A1 · Huber · 2002 [cited by examiner]
US 20020065678A1 · Peliotis · 2002 [cited by examiner]
US 20020120931A1 · Huber · 2002 [cited by examiner]
US 20020147987A1 · Reynolds · 2002 [cited by examiner]
US 20030028873A1 · Lemmons · 2003 [cited by examiner]
US 20030149983A1 · Markel · 2003 [cited by examiner]
US 20070226761A1 · Zalewski · 2007 [cited by examiner]
US 20080080009A1 · Masui · 2008 [cited by examiner]
US 20100321389A1 · Gay · 2010 [cited by examiner]
US 20110249074A1 · Cranfill · 2011 [cited by examiner]
US 20120038739A1 · Welch · 2012 [cited by examiner]
US 20120050492A1 · Moriwake · 2012 [cited by examiner]
US 20120057045A1 · Shimizu · 2012 [cited by examiner]
US 20130031582A1 · Tinsman · 2013 [cited by examiner]
US 20140068692A1 · Archibong · 2014 [cited by examiner]
US 20160299563A1 · Stafford · 2016 [cited by examiner]
US 20170141847A1 · De Bruijn · 2017 [cited by examiner]
US 20170366867A1 · Davies · 2017 [cited by examiner]
US 20180084302A1 · Chen · 2018 [cited by examiner]
US 20180310066A1 · Kobayashi · 2018 [cited by examiner]
US 20190179405A1 · Sun · 2019 [cited by examiner]
US 20200029069A1 · Goergen · 2020 [cited by examiner]
US 20210388671A1 · Kirkeby · 2021 [cited by examiner]
US 20220239988A1 · Yang · 2022 [cited by examiner]
US 20220261951A1 · Renschler · 2022 [cited by examiner]
US 20230013539A1 · Holland · 2023 [cited by examiner]
US 20230138677A1 · Kwong · 2023 [cited by examiner]
US 20230409749A1 · Li · 2023 [cited by examiner]
US 20240371185A1 · Sadek · 2024 [cited by examiner]
US 20240398229A1 · Mehndiratta · 2024 [cited by examiner]
Lin et al.; “Real-Time High-Resolution Background Matting”; IEEE/CVF Conf. on Computer Vision and Pattern Recognition; 2021; p. 8762-8771. [cited by applicant]
Ke et al.; “MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition”; 36 [cited by applicant]
Lin et al.; “Robust High-Resolution Video Matting With Temporal Guidance”; IEEE/CVF Winter Conf. on Applications of Computer Vision; 2022; p. 238-247. [cited by applicant]
Mur-Artal et al.; “ORB-SLAM: A Versatile and Accurate Monocular SLAM System”; IEEE Transactions on Robotics; vol. 31; 2015; p. 1147-1163. [cited by applicant]
Hang et al.; “SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization”; IEEE/CVF Conf. on Computer Vision and Pattern Recognition; 2022; p. 19710-19719. [cited by applicant]
Z. Zhang: “A Flexible New Technique for Camera Calibration”; Technical Report MSR-TR-98-71; Microsoft Corporation; Mar. 1999; 22 pages. [cited by applicant]
T. Williams; “What is Amazon VPP?”; https://www.envisionhorizons.com/what-is-amazon-vpp/; Envision Horizons; May 2022; accessed Jan. 29, 2025; 15 pages. [cited by applicant]