IP Library Granted Patent US 12,437,464
Granted Patent B2
US 12,437,464 · App. 18/369,721 · Granted Oct 7, 2025

Method and apparatus, electronic device, computer-readable storage medium, and computer program product for performing real-time image rendering of virtual objects

Inventors: Fei Xia (Shenzhen, CN); Fei Ling (Shenzhen, CN); Yongxiang Zhang (Shenzhen, CN); Jun Deng (Shenzhen, CN)
Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
G06T15/04G06T7/90G06V10/54G06V10/751
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 12,437,464
App. No.
18/369,721
Granted
Oct 7, 2025
Kind
B2
Abstract

This application provides an image rendering method performed by an electronic device. The method includes: acquiring first texture data of a virtual object and conversion parameters corresponding to second texture data of the virtual object; performing, based on the conversion parameters and the first texture data, fitting rendering to obtain a fitted rendering image comprising the virtual object; updating the conversion parameters and the first texture data based on a rendering loss between the fitted rendering image and a reference rendering image comprising the virtual object , wherein the reference rendering image is a rendering image that is obtained by performing rendering based on the second texture data; and performing, based on the updated conversion parameters and the updated first texture data, real-time rendering to obtain a target rendering image comprising the virtual object.

Claims (70)

1. An image rendering method performed by an electronic device and the method comprising:

acquiring, by the electronic device, first texture data of a virtual object and conversion parameters corresponding to second texture data of the virtual object;

performing, by the electronic device, based on the conversion parameters and the first texture data, fitting rendering to obtain a fitted rendering image comprising the virtual object;

updating, by the electronic device, the conversion parameters and the first texture data based on a rendering loss between the fitted rendering image and a reference rendering image comprising the virtual object, wherein the reference rendering image is a rendering image that is obtained by performing rendering based on the second texture data; and

performing, by the electronic device, based on the updated conversion parameters and the updated first texture data, real-time rendering to obtain a target rendering image comprising the virtual object.

2. The method according to claim 1 , wherein the performing, by the electronic device, based on the conversion parameters and the first texture data, fitting rendering to obtain a fitted rendering image comprising the virtual object comprises:

performing, by the electronic device, based on the conversion parameters, space conversion on the first texture data of the virtual object toward the second texture data to obtain third texture data, wherein the third texture data is located in a same dynamic range space as the second texture data; and

performing, by the electronic device, based on the third texture data, fitting rendering to obtain the fitted rendering image comprising the virtual object.

3. The method according to claim 2 , wherein the third texture data comprises a third color value of each texture pixel; and

the performing, by the electronic device, based on the third texture data, fitting rendering corresponding to the virtual object to obtain the fitted rendering image comprising the virtual object comprises:

acquiring, by the electronic device, two-dimensional texture coordinates of the virtual object;

acquiring, by the electronic device, a differentiable rendering framework corresponding to fitting rendering; and

performing, by the electronic device, forward propagation on the two-dimensional texture coordinates and the third color value of each texture pixel in the differentiable rendering framework to obtain the fitted rendering image comprising the virtual object.

4. The method according to claim 1 , wherein the rendering loss between the fitted rendering image and the reference rendering image is defined by:

determining, by the electronic device, an overall pixel value difference between a standard rendering image and the fitted rendering image in a screen space; and

determining, by the electronic device, the rendering loss based on the overall pixel value difference, a length of the fitted rendering image, and a width of the fitted rendering image.

5. The method according to claim 1 , wherein the updating, by the electronic device, the conversion parameters and the first texture data based on the rendering loss comprises:

performing, by the electronic device, based on the rendering loss, partial derivative processing on the first texture data to obtain a gradient corresponding to the first texture data;

performing, by the electronic device, based on the rendering loss, partial derivative processing on the conversion parameters to obtain a gradient corresponding to the conversion parameters; and

updating, by the electronic device, the first texture data based on the gradient corresponding to the first texture data, and updating the conversion parameters based on the gradient corresponding to the conversion parameters.

6. The method according to claim 1 , wherein the performing, by the electronic device, based on the updated conversion parameters and the updated first texture data, real-time rendering on the virtual object comprises:

performing, by the electronic device, when the rendering loss is less than a loss threshold, real-time rendering on the virtual object based on the updated conversion parameters and the updated first texture data; and

performing, by the electronic device, when a number of updates of the conversion parameters and the first texture data reaches a threshold of the number of updates, real-time rendering on the virtual object based on the updated conversion parameters and the updated first texture data.

7. The method according to claim 1 , wherein the performing, by the electronic device, based on the updated conversion parameters and the updated first texture data, real-time rendering on the virtual object to obtain a target rendering image comprising the virtual object comprises:

performing, by the electronic device, based on the updated conversion parameters, space conversion on the updated first texture data toward the second texture data to obtain fourth texture data, wherein the fourth texture data is located in the same dynamic range space as the second texture data;

determining, by the electronic device, at least one two-dimensional texture coordinate of the virtual object;

sampling, by the electronic device, from the fourth texture data, a texture image corresponding to the two-dimensional texture coordinate, and mapping the texture image obtained by sampling; and

generating, by the electronic device, based on a mapping result of each two-dimensional texture coordinate, the target rendering image comprising the virtual object.

8. The method according to claim 1 , wherein a data size of the first texture data is smaller than a data size of the second texture data.

9. The method according to claim 1 , wherein an image information range of the first texture data being smaller than an image information range of the second texture data.

10. An electronic device, comprising:

a memory, configured to store computer-executable instructions; and

a processor, configured to, when executing the computer-executable instructions stored in the memory, cause the electronic device to implement an image rendering method including:

acquiring, by the electronic device, first texture data of a virtual object and conversion parameters corresponding to second texture data of the virtual object;

performing, by the electronic device, based on the conversion parameters and the first texture data, fitting rendering to obtain a fitted rendering image comprising the virtual object;

updating, by the electronic device, the conversion parameters and the first texture data based on a rendering loss between the fitted rendering image and a reference rendering image comprising the virtual object, wherein the reference rendering image is a rendering image that is obtained by performing rendering based on the second texture data; and

performing, by the electronic device, based on the updated conversion parameters and the updated first texture data, real-time rendering to obtain a target rendering image comprising the virtual object.

11. The electronic device according to claim 10 , wherein the performing, by the electronic device, based on the conversion parameters and the first texture data, fitting rendering to obtain a fitted rendering image comprising the virtual object comprises:

performing, by the electronic device, based on the conversion parameters, space conversion on the first texture data of the virtual object toward the second texture data to obtain third texture data, wherein the third texture data is located in a same dynamic range space as the second texture data; and

performing, by the electronic device, based on the third texture data, fitting rendering to obtain the fitted rendering image comprising the virtual object.

12. The electronic device according to claim 11 , wherein the third texture data comprises a third color value of each texture pixel; and

the performing, by the electronic device, based on the third texture data, fitting rendering corresponding to the virtual object to obtain the fitted rendering image comprising the virtual object comprises:

acquiring, by the electronic device, two-dimensional texture coordinates of the virtual object;

acquiring, by the electronic device, a differentiable rendering framework corresponding to fitting rendering; and

performing, by the electronic device, forward propagation on the two-dimensional texture coordinates and the third color value of each texture pixel in the differentiable rendering framework to obtain the fitted rendering image comprising the virtual object.

13. The electronic device according to claim 10 , wherein the rendering loss between the fitted rendering image and the reference rendering image is defined by:

determining, by the electronic device, an overall pixel value difference between a standard rendering image and the fitted rendering image in a screen space; and

determining, by the electronic device, the rendering loss based on the overall pixel value difference, a length of the fitted rendering image, and a width of the fitted rendering image.

14. The electronic device according to claim 10 , wherein the updating, by the electronic device, the conversion parameters and the first texture data based on the rendering loss comprises:

performing, by the electronic device, based on the rendering loss, partial derivative processing on the first texture data to obtain a gradient corresponding to the first texture data;

performing, by the electronic device, based on the rendering loss, partial derivative processing on the conversion parameters to obtain a gradient corresponding to the conversion parameters; and

updating, by the electronic device, the first texture data based on the gradient corresponding to the first texture data, and updating the conversion parameters based on the gradient corresponding to the conversion parameters.

15. The electronic device according to claim 10 , wherein the performing, by the electronic device, based on the updated conversion parameters and the updated first texture data, real-time rendering on the virtual object comprises:

performing, by the electronic device, when the rendering loss is less than a loss threshold, real-time rendering on the virtual object based on the updated conversion parameters and the updated first texture data; and

performing, by the electronic device, when a number of updates of the conversion parameters and the first texture data reaches a threshold of the number of updates, real-time rendering on the virtual object based on the updated conversion parameters and the updated first texture data.

16. The electronic device according to claim 10 , wherein the performing, by the electronic device, based on the updated conversion parameters and the updated first texture data, real-time rendering on the virtual object to obtain a target rendering image comprising the virtual object comprises:

performing, by the electronic device, based on the updated conversion parameters, space conversion on the updated first texture data toward the second texture data to obtain fourth texture data, wherein the fourth texture data is located in the same dynamic range space as the second texture data;

determining, by the electronic device, at least one two-dimensional texture coordinate of the virtual object;

sampling, by the electronic device, from the fourth texture data, a texture image corresponding to the two-dimensional texture coordinate, and mapping the texture image obtained by sampling; and

generating, by the electronic device, based on a mapping result of each two-dimensional texture coordinate, the target rendering image comprising the virtual object.

17. The electronic device according to claim 10 , wherein a data size of the first texture data is smaller than a data size of the second texture data.

18. The electronic device according to claim 10 , wherein an image information range of the first texture data being smaller than an image information range of the second texture data.

19. A non-transitory computer-readable storage medium, storing computer-executable instructions that, when executed by a processor of an electronic device, causes the electronic device to implement an image rendering method including:

acquiring, by the electronic device, first texture data of a virtual object and conversion parameters corresponding to second texture data of the virtual object;

performing, by the electronic device, based on the conversion parameters and the first texture data, fitting rendering to obtain a fitted rendering image comprising the virtual object;

updating, by the electronic device, the conversion parameters and the first texture data based on a rendering loss between the fitted rendering image and a reference rendering image comprising the virtual object, wherein the reference rendering image is a rendering image that is obtained by performing rendering based on the second texture data; and

performing, by the electronic device, based on the updated conversion parameters and the updated first texture data, real-time rendering to obtain a target rendering image comprising the virtual object.

20. The non-transitory computer-readable storage medium according to claim 19 , wherein the performing, by the electronic device, based on the conversion parameters and the first texture data, fitting rendering to obtain a fitted rendering image comprising the virtual object comprises:

performing, by the electronic device, based on the conversion parameters, space conversion on the first texture data of the virtual object toward the second texture data to obtain third texture data, wherein the third texture data is located in a same dynamic range space as the second texture data; and

performing, by the electronic device, based on the third texture data, fitting rendering to obtain the fitted rendering image comprising the virtual object.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 19, 2023
From: XIA, FEI; LING, FEI; ZHANG, YONGXIANG; DENG, JUN
To: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Reel/Frame 064959/0249 →
Continuity (2)
Continuation PCTCN2022136193 · Dec 2, 2022
Related Publication 20240005588A1 · Jan 4, 2024
References Cited (20)
US 6078334A · Hanaoka · 2000 [cited by examiner]
US 7932914B1 · Geiss et al. · 2011 [cited by applicant]
US 20160078667A1 · Shim · 2016 [cited by examiner]
US 20200151509A1 · Sunkavalli et al. · 2020 [cited by applicant]
US 20210279952A1 · Chen · 2021 [cited by examiner]
US 20230140460A1 · Munkberg · 2023 [cited by examiner]
CN 102696220A · 2012 [cited by applicant]
CN 106033617A · 2016 [cited by applicant]
CN 113963110A · 2022 [cited by applicant]
CN 114067042A · 2022 [cited by applicant]
WO WO2022103877A1 · 2022 [cited by examiner]
Tencent Technology (Shenzhen) Company Limited, ISR, PCT/CN2022/136193, Feb. 22, 2023, 3 pgs. [cited by applicant]
Tencent Technology, WO, PCT/CN2022/136193, Feb. 22, 2023, 4 pgs. [cited by applicant]
Tencent Technology, IPRP, PCT/CN2022/136193, Aug. 30, 2024, 5 pgs. [cited by applicant]
Tencent Technology, Extended European Search Report, EP Patent Application No. 22929625.6, Feb. 12, 2025, 9 pgs. [cited by applicant]
Francesco Banterle et al., “Expanding Low Dynamic Range Videos for High Dynamic Range Applications”, SCCG '08: Proceedings of the 24th Spring Conference on Computer Graphics, Apr. 2008, 10 pgs. [cited by applicant]
Francesco Banterle et al., “Inverse Tone Mapping”, Graphite '06: Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, Nov. 2006, 9 pgs. [cited by applicant]
Hanning Yu et al., “Luminance Attentive Networks for HDR Image and Panorama Reconstruction”, Computer Graphics Forum, Image Synthesis and Enhancement, vol. 40, Issue 7, Sep. 2021, 21 pgs. [cited by applicant]
Jinghui Li et al., “Hornet: Single-lmage-Based HDR Reconstruction Using Channel Attention CNN”, ICMSSP '19: Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing, May 2019, 6 p… [cited by applicant]
Jon Hasselgren et al., “Appearance-Driven Automatic 3D Model Simplification”, Eurographics Symposium on Rendering (DL-only Track), Apr. 2021, 19 pgs. [cited by applicant]