IP Library › Granted Patent US 12,505,612
Granted Patent B2
US 12,505,612 · App. 18/243,449 · Granted Dec 23, 2025

Systems and methods for dynamic three-dimensional model lighting and realistic shadow rendering in automotive mixed reality applications

Inventors: Christopher Nowakowski (San Mateo, CA); Anthony Amos (San Mateo, CA); Anushalakshmi Manila (San Mateo, CA); Jaime Almeida (San Mateo, CA); Nicodemus Estee (San Mateo, CA); Sonam Negi (San Mateo, CA)
Assignee: Valeo Comfort and Driving Assistance
G06T15/506G06T15/80G06T19/006
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 12,505,612
App. No.
18/243,449
Granted
Dec 23, 2025
Kind
B2
Abstract

A method for generating a virtual rendering includes receiving first image data that includes a plurality of images. Each image of the plurality of images may correspond to an environment of a non-virtual object. The method also includes determining a current position of a light source relative to the non-virtual object, determining a current intensity value of the light source, and generating a virtual rendering of the non-virtual object using the plurality of images, the current position of the light source relative to the non-virtual object, and the current intensity value of the light source. The method also includes providing, at a display, the virtual rendering.

Claims (46)

1 . A method for generating a virtual rendering, the method comprising:

receiving first image data that includes a plurality of images, each image of the plurality of images corresponding to an environment of a non-virtual object and including one or more other non-virtual objects;

determining a current position of a light source relative to the non-virtual object;

determining a current intensity value of the light source;

generating a virtual rendering of the non-virtual object using the plurality of images;

generating an adjusted virtual rendering of the non-virtual object by adjusting at least one shadow of the virtual rendering of the non-virtual object based on the current position of the light source relative to the non-virtual object, and the current intensity value of the light source;

generating video data using second image data and the adjusted virtual rendering of the non-virtual object, wherein the video data includes the one or more other non-virtual objects and the adjusted virtual rendering of the non-virtual object; and

providing, at a display, the video data.

2 . The method of claim 1 , wherein the first image data is captured using at least one image capturing device.

3 . The method of claim 2 , wherein the at least one image capturing device is disposed on at least one of an exterior portion of the non-virtual object and an interior portion of the non-virtual object.

4 . The method of claim 3 , wherein the non-virtual object includes a vehicle.

5 . The method of claim 1 , wherein the first image data is at least one of captured in real-time and captured at a time prior to a time corresponding to the current position of the light source relative to the non-virtual object.

6 . The method of claim 1 , wherein determining the current position of the light source relative to the non-virtual object is based on global position system coordinates corresponding to the non-virtual object.

7 . The method of claim 1 , wherein determining the current position of the light source relative to the non-virtual object is based on a time of day.

8 . The method of claim 1 , wherein determining the current position of the light source relative to the non-virtual object is based on sunload data received from a sunload sensor of the non-virtual object.

9 . The method of claim 1 , wherein determining the current position of the light source relative to the non-virtual object is based on second image data received from one or more image capturing devices associated with the non-virtual object.

10 . The method of claim 9 , further comprising providing the second image data to an artificial intelligence engine that uses at least one machine learning model to provide at least one prediction, wherein the at least one prediction indicates a predicted current position of the light source relative to the non-virtual object, and wherein determining the current position of the light source relative to the non-virtual object is based on the at least one prediction.

11 . The method of claim 1 , wherein light from the light source includes sun light.

12 . The method of claim 1 , wherein the light source includes a street light.

13 . The method of claim 1 , wherein determining the current intensity value of the light source is based on global position system coordinates corresponding to the non-virtual object.

14 . The method of claim 1 , wherein determining the current intensity value of the light source is based on a time of day.

15 . The method of claim 1 , wherein determining the current intensity value of the light source is based on sunload data received from a sunload sensor of the non-virtual object.

16 . The method of claim 1 , further comprising selectively adjusting at least one aspect of the virtual rendering based on a change in at least one of the current position of the light source relative to the non-virtual object and the current intensity value of the light source.

17 . The method of claim 16 , wherein the change in the at least one of the current position of the light source relative to the non-virtual object and the current intensity value of the light source corresponds to at least one of a change in position of the non-virtual object and a change in an exposure of light from the light source on the non-virtual object.

18 . The method of claim 1 , further comprising selectively adjusting at least one aspect of the virtual rendering periodically based on change in a time of day.

19 . A system for generating a virtual rendering, the system comprising:

a processor; and

a memory including instructions that, when executed by the processor, cause the processor to:

receive first image data that includes a plurality of images, each image of the plurality of images corresponding to an environment of a non-virtual object and including one or more other non-virtual objects;

determine a current position of a light source relative to the non-virtual object;

determine a current intensity value of the light source;

generate a virtual rendering of the non-virtual object using the plurality of images;

generate an adjusted virtual rendering of the non-virtual object by adjusting at least one shadow of the virtual rendering of the non-virtual object based on the current position of the light source relative to the non-virtual object, and the current intensity value of the light source;

generate video data using second image data and the adjusted virtual rendering of the non-virtual object, wherein the video data includes the one or more other non-virtual objects and the adjusted virtual rendering of the non-virtual object; and

provide, at a display, the video data.

20 . An apparatus generating a virtual rendering of a vehicle, the apparatus comprising:

a vehicle controller configured to:

receive first image data that includes a plurality of images, each image of the plurality of images corresponding to an environment of a vehicle and including one or more non-virtual objects;

determine a current position of at least one light source relative to the vehicle;

determine a current intensity value of the at least one light source;

generate a virtual rendering of the vehicle using the plurality of images;

position a virtual light source in the virtual rendering based on the current position of the at least one light source relative to the vehicle;

adjust an intensity value of the virtual light source based on the current intensity value of the at least one light source;

generate an adjusted virtual rendering of the vehicle by adjusting at least one shadow of the virtual rendering of the vehicle based on the position of the virtual light source and the intensity value;

generate video data using second image data and the adjusted virtual rendering of the vehicle, wherein the video data includes the one or more non-virtual objects and the adjusted virtual rendering of the vehicle; and

provide, at a display of the vehicle, the video data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 7, 2023
From: NOWAKOWSKI, CHRISTOPHER; AMOS, ANTHONY; MANILA, ANUSHALAKSHMI; ALMEIDA, JAIME; ESTEE, NICODEMUS; NEGI, SONAM
To: VALEO COMFORT AND DRIVING ASSISTANCE
Reel/Frame 064832/0845 →
Continuity (1)
Related Publication 20250086884A1 · Mar 13, 2025
References Cited (22)
US 8576285B2 · Gomi · 2013 [cited by examiner]
US 9633266B2 · Shimizu · 2017 [cited by examiner]
US 9881414B2 · Lee · 2018 [cited by examiner]
US 10354449B2 · Todeschini · 2019 [cited by applicant]
US 10657721B2 · Yin et al. · 2020 [cited by applicant]
US 10735667B1 · Kida · 2020 [cited by examiner]
US 11631151B2 · Cella · 2023 [cited by applicant]
US 20130293582A1 · Ng-Thow-Hing · 2013 [cited by examiner]
US 20140160100A1 · Edgren · 2014 [cited by examiner]
US 20160364914A1 · Todeschini · 2016 [cited by applicant]
US 20190315275A1 · Kim · 2019 [cited by examiner]
US 20240171724A1 · Irshad · 2024 [cited by examiner]
US 20240355060A1 · Jeppe · 2024 [cited by examiner]
US 20240362793A1 · Raj · 2024 [cited by examiner]
US 20250115265A1 · Ishiyama · 2025 [cited by examiner]
DE 102018100599A1 · 2019 [cited by applicant]
EP 2741260A1 · 2014 [cited by applicant]
WO 2022104295A1 · 2021 [cited by applicant]
Jonas Trottnow et al. “Intuitive Virtual Production Tools for Set and Light Editing.” CVMP 2015, Nov. 24-25, 2015, London, United Kingdom, 8 pages. [cited by applicant]
Jinsong Zhang et al. “All-Weather Deep Outdoor Lighting Estimation.” 2019 IEE/CVR Conference on computer Vision and Pattern Recognition (CVPR), pp. 10150-10158. [cited by applicant]
Written Opinion and International Search Report for PCT/US2024/045340, Dated Nov. 12, 2024, All together 12 Pages. [cited by applicant]
Website https://www.fujitsu.com/us/Images/360_OmniView_AppNote.pdf Author Unknown, FUJltSU, “360° Wrap-Around Video Imaging Technology Ready for Integration with Fujitsu Graphics SoCs.” Dated Jan. 2014, 7 Pages. [cited by applicant]