Systems and methods for performing video conversion based on non-linear stretch information
AssigneeCyberlink Corp.
InventorsChih-Yu Cheng, Ho Chao Huang, Wei-Hsin Tseng
Life of this patent
Estimating the term…
Abstract
A method implemented in a computing system for converting two-dimensional (2D) video to three-dimensional (3D) format comprises sampling the 2D video, wherein the sampling is performed non-linearly in one or more directions. The method further comprises determining depth information of one or more objects within the 2D video based on sampling information and transforming the 2D video to a 3D-compatible format according to the sampling and the depth information.
Claims25
A method implemented in a computing system for converting two-dimensional (2D) video to three-dimensional (3D) video, comprising:
- sampling the 2D video according to a sampling density, wherein the sampling is performed non-linearly in one or more spatial directions, and wherein at least part of the sampling density is adjusted according to a saliency region;
- determining depth information of one or more objects within the 2D video based on sampling information;
- and
- transforming the 2D video to a 3D-compatible format according to the sampling and the depth information.
A video system for converting two-dimensional (2D) video to three-dimensional (3D) format video, comprising:
- a sampling module configured to perform non-linear sampling of the 2D video in one or more spatial directions according to a sampling density;
- a depth processor configured to determine depth information relating to objects in the 2D video based on sampling information;
- a saliency region identifier configured to identify one or more regions of interest with a frame, wherein the sampling module is further configured to adjust the sampling density for the sampling based on a saliency region;
- and
- a graphics renderer for rendering a 3D video according to the sampling density and the depth information.
A method implemented in a computing system for converting two-dimensional (2D) video to three-dimensional (3D) video, comprising:
- defining a high saliency region;
- adjusting a sampling density according to the high saliency region and the depth information, wherein the sampling density is utilized for performing non-linear sampling in one or more spatial directions;
- determining depth information relating to objects within the high saliency region based on sampling information;
- sampling the 2D video according to the adjusted sampling density;
- transforming the 2D video to a 3D-compatible format according to the sampling and depth information;
- and
- outputting the transformed 2D video to a display device.
Dependencies are inferred from the claim text.