Method and apparatus for rendering 3D polygon meshes using multi-view textures
AssigneeFXGear Inc.
InventorKyung Gun Na
Life of this patent
Estimating the term…
Abstract
An apparatus for rendering a three-dimensional (3D) polygon mesh includes a processor, and a memory storing instructions, wherein the processor is configured to execute the instructions to obtain a plurality of multi-view images corresponding to a plurality of captured images obtained by capturing an object at different capture camera positions, obtain a 3D polygon mesh for the object, select one or more of the plurality of multi-view images as one or more texture images based on a render camera position and capture camera positions of the plurality of multi-view images, and render the 3D polygon mesh as a two-dimensional (2D) image based on the selected one or more texture images.
Claims18
An apparatus for rendering a three-dimensional (3D) polygon mesh, the apparatus comprising:
- a processor;
- and
- a memory storing instructions,
- wherein the processor is configured to execute the instructions to:
- obtain a plurality of multi-view images corresponding to a plurality of captured images obtained by capturing an object at different capture camera positions,
- obtain a 3D polygon mesh for the object,
- determine a weight of each of the plurality of multi-view images based on a render camera position and the capture camera positions of the plurality of multi-view images,
- select one or more of the plurality of multi-view images as one or more texture images based on the weights of the plurality of multi-view images, and
- render the 3D polygon mesh as a two-dimensional (2D) image based on the selected one or more texture images,
- wherein the weights are determined such that an error between a weighted sum of capture camera position vectors of the plurality of multi-view images based on a position of a first point of the 3D polygon mesh according to the weights and a render camera position vector based on the position of the first point is minimized.
An operating method of an apparatus for rendering a three-dimensional (3D) polygon mesh, the operating method comprising:
- obtaining a plurality of multi-view images corresponding to a plurality of captured images obtained by capturing an object at different capture camera positions;
- obtaining a 3D polygon mesh for the object;
- determining a weight of each of the plurality of multi-view images based on a render camera position and the capture camera positions of the plurality of multi-view images;
- selecting one or more of the plurality of multi-view images as one or more texture images based on the weights of the plurality of multi-view images;
- and
- rendering the 3D polygon mesh as a two-dimensional (2D) image based on the selected one or more texture images,
- wherein the weights are determined such that an error between a weighted sum of capture camera position vectors of the plurality of multi-view images based on a position of a first point of the 3D polygon mesh according to the weights and a render camera position vector based on the position of the first point is minimized.
Dependencies are inferred from the claim text.