Real-time non-photo-realistic rendering

Number: 12260484
Published: 2025-03-25
Filed: 2022-10-21
Assignee: Disney Enterprises, Inc.
Inventors: Stifter; Megan et al.
CPC: A63F13/52; G06T15/02; A63F13/60; G06T5/50; G06T5/70; G06T15/005
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Real-time non-photorealistic rendering technique.

Abstract

According to one exemplary implementation, a system includes processing hardware and a system memory storing a non-photo-realistic (NPR) renderer. The processing hardware is configured to execute the NPR renderer to receive a digital asset, display a preliminary image corresponding to the digital asset, and receive editing data identifying an NPR effect. The processing hardware is further configured to execute the software code to produce the NPR image, in a consolidated rendering and compositing process and in real-time with respect to receiving the editing data, using the preliminary image and the editing data.

Background

BACKGROUND (1) Game engines have traditionally been built on a graphics foundation that focuses on achieving the highest quality of photo-realistic rendering possible at a high frame-rate to allow for user interaction. By contrast, non-photo-realistic (NPR) rendering refers to different approaches to render engineering that result in images that don't mimic real-life, but instead focus on creating a certain look that mimics different formats and mediums, or that can be art directed to achieve aesthetic looks and styles that have never before been seen. However, existing solutions for performing NPR rendering using offline renderers typically require undesirably long render times, such as several hours per frame, as well as several render passes compiled in compositing software. Consequently, there is a need in the art for an NPR rendering solution enabling the real-time production of NPR images at high frame-rates in a cohesive package.

Claims

1. A method for use by a system including processing hardware and a system memory storing a non-photo-realistic (NPR) renderer, the method comprising: receiving, by the NPR renderer executed by the processing hardware, a digital asset; displaying, by the NPR renderer executed by the processing hardware, a preliminary image corresponding to the digital asset; receiving, by the NPR renderer executed by the processing hardware, editing data identifying an NPR effect; and producing the NPR image, by the NPR renderer executed by the processing hardware in a consolidated rendering and compositing process and in real-time with respect to receiving the editing data, using the preliminary image and the editing data; wherein the NPR renderer includes at least one machine learning model trained to predict, based on the editing data and the digital asset, one or more operating parameters for use by the NPR renderer when rendering and compositing the NPR image. || 9. A system comprising: processing hardware and a system memory storing a non-photo-realistic (NPR) renderer; the processing hardware configured to execute the NPR renderer to: receive a digital asset; display a preliminary image corresponding to the digital asset; receive editing data identifying an NPR effect; and produce an NPR image, in a consolidated rendering and compositing process and in real-time with respect to receiving the editing data, using the preliminary image and the editing data; wherein the NPR renderer includes at least one machine learning model trained to predict, based on the editing data and the digital asset, one or more operating parameters for use by the NPR renderer when rendering and compositing the NPR image.