Adaptive rendering with linear predictions

Number: 9892549
Published: 2018-02-13
Filed: 2016-06-15
Assignee: Pixar
Inventors: Mitchell; Kenneth; Moon; Bochang; Iglesias-Guitian; Jose A.
CPC: G06T15/00
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Adaptive rendering with linear predictions.

Abstract

Systems, methods and articles of manufacture for rendering an image. Embodiments include selecting a plurality of positions within the image and constructing a respective linear prediction model for each selected position. A respective prediction window is determined for each constructed linear prediction model. Additionally, embodiments render the image using the linear prediction models using the constructed linear prediction models, where at least one of the constructed linear prediction models is used to predict values for two or more of a plurality of pixels of the image, and where a value for at least one of the plurality of pixels is determined based on two or more of the constructed linear prediction models.

Background

BACKGROUNDField of the Invention(1) Embodiments disclosed herein relate to computer-generated imagery (CGI) and computer-aided animation, and more specifically, this disclosure relates to techniques for efficiently rendering images using a select number of linear prediction models of varying prediction sizes.Description of the Related Art(2) With the increasingly wide-spread availability of computers, many graphic artists and animators rely upon computers to assist in the production process for the creation of animations, computer-generated imagery (CGI) and the like. In doing so, the artists and animators may create virtual models stored in computer memory that represent physical models or other entities (e.g., fictitious characters). Typically, two-dimensional (2D) or three-dimensional (3D) computer-aided animation combines 2D/3D models of objects and programmed movement of one or more of the models. In 3D computer animation, an object modeling process can be used in which objects are sculpted, akin to working with real day or plaster, working from general forms to specific details, for example, with various sculpting tools. Models may be constructed, for example, out of geometrical vertices, faces, and edges in a 3D coordinate system to represent the objects. These virtual models can be manipulated using computers to, for example, simulate physics, design aesthetic actions such as poses or other deformations, create lighting, coloring and paint, or the like, of characters

Claims

1. A method of rendering an image, comprising: selecting a plurality of positions within the image; constructing a respective linear prediction model for each selected position, wherein a respective prediction window is determined for each constructed linear prediction model; and rendering the image using the constructed linear prediction models to predict values for each of a plurality of pixels of the image, wherein at least one of the constructed linear prediction models is used to predict values for two or more of the plurality of pixels of the image, and wherein a value for at least one of the plurality of pixels is determined based on two or more of the constructed linear prediction models. 13. A non-transitory computer-readable medium containing computer program code that, when executed by operation of one or more computer processors, performs an operation for rendering an image, the operation comprising: selecting a plurality of positions within the image; constructing a respective linear prediction model for each selected position, wherein a respective prediction window is determined for each constructed linear prediction model; and rendering the image using the constructed linear prediction models to predict values for each of a plurality of pixels of the image, wherein at least one of the constructed linear prediction models is used to predict values for two or more of the plurality of pixels of the image, and wherein a value for at least one of the plurality of pixels is determined based on two or more of the constructed linear prediction models. 20. A system, comprising: one or more computer processors; and a non-transitory memory containing computer program code that, when executed by operation of the one or more computer processors, performs an operation for rendering an image, the operation comprising: selecting a plurality of positions within the image; constructing a respective linear prediction model for each selected position, wherein a respective prediction window is determined for each constructed linear prediction model; and rendering the image using the constructed linear prediction models to predict values for each of a plurality of pixels of the image, wherein at least one of the constructed linear prediction models is used to predict values for two or more of the plurality of pixels of the image, and wherein a value for at least one of the plurality of pixels is determined based on two or more of the constructed linear prediction models.