US 10,504,274 B2 · Fusing, texturing, and rendering views of dynamic three-dimensional models

Abstract

Various approaches described herein improve the quality of results when fusing depth maps to generate dynamic three-dimensional (“3D”) models, applying texture details to dynamic 3D models, or rendering views of textured, dynamic 3D models. For example, when fusing depth maps to generate a dynamic 3D model, a fusion component can also incorporate intrinsic color values for points of the dynamic 3D model, potentially making the dynamic 3D model more accurate, especially for areas in which depth values are not reliable or not available. As another example, when applying texture details, a rendering component can apply smoothed, viewpoint-dependent texture weights to texture values from different texture maps, which can reduce blurring and avoid the introduction of noticeable seams. As another example, a rendering component can apply special effects indicated by metadata to rendered views, thereby allowing a content provider to assert artistic control over presentation.

Claims28

Dependent claims

In a computer system, a method of texturing a dynamic three-dimensional (“3D”) model of a computer-represented environment, the method comprising:

receiving texture maps for a current frame, each of the texture maps including texture values captured from a different input viewpoint in the computer-represented environment;
receiving model data for the current frame, the model data including points of the dynamic 3D model of the computer-represented environment;
determining texture weights for the current frame for at least some of the points of the dynamic 3D model, including smoothing at least some of the texture weights for the current frame temporally relative to previous texture weights;
for the at least some of the points of the dynamic 3D model, applying corresponding texture values from the texture maps according to the smoothed texture weights for the current frame;
and
rendering a view of the textured, dynamic 3D model from an output viewpoint.

3 more elements

A computer system comprising one or more processing units and memory, wherein the computer system implements a tool for texturing a dynamic three-dimensional (“3D”) model of a computer-represented environment, the tool comprising:

one or more buffers, in the memory, configured to receive:
texture maps for a current frame, each of the texture maps including texture values captured from a different input viewpoint in the computer-represented environment;
and
model data for the current frame, the model data including points of the dynamic 3D model of the computer-represented environment;
and
a rendering component configured to:
determine texture weights for the current frame for at least some of the points of the dynamic 3D model, wherein the rendering component is configured to smooth at least some of the texture weights for the current frame temporally relative to previous texture weights;
for the at least some of the points of the dynamic 3D model, apply corresponding texture values from the texture maps according to the smoothed texture weights for the current frame;
and
render a view of the textured, dynamic 3D model from an output viewpoint.

7 more elements

One or more computer-readable media storing computer-executable instructions for causing a computer system, when programmed thereby, to perform operations to texture a dynamic three-dimensional (“3D”) model of a computer-represented environment, the operations comprising:

receiving texture maps for a current frame, each of the texture maps including texture values captured from a different input viewpoint in the computer-represented environment;
receiving model data for the current frame, the model data including points of the dynamic 3D model of the computer-represented environment;
determining texture weights for the current frame for at least some of the points of the dynamic 3D model, including smoothing at least some of the texture weights for the current frame temporally relative to previous texture weights;
and
for the at least some of the points of the dynamic 3D model, applying corresponding texture values from the texture maps according to the smoothed texture weights for the current frame;
and
rendering a view of the textured, dynamic 3D model from an output viewpoint.

4 more elements

Dependencies are inferred from the claim text.

Fusing, texturing, and rendering views of dynamic three-dimensional models

Life of this patent

Fusing, texturing, and rendering views of dynamic three-dimensional models

Life of this patent

Abstract

Claims28