System and method of rendering stereoscopic images
AssigneeHimax Technologies Limited
InventorTzung-Ren Wang
Life of this patent
Estimating the term…
Abstract
In some embodiments, a method of rendering a stereoscopic image based on a two-dimensional image frame and a depth map comprises generating a saliency map of the two-dimensional image frame, determining a region where is located an object of focus from the saliency map, modifying the depth map such that a range of depth values in the depth map that is associated the object of focus is redistributed toward a depth level of a display screen, and generating a virtual stereoscopic image frame based on the modified depth map and the two-dimensional image frame. In other embodiments, systems of rendering stereoscopic images are also described.
Claims19
A method applicable on a processing unit to form a stereoscopic image based on a two-dimensional image frame and a depth map associated therewith, the method comprising:
- generating a saliency map of the two-dimensional image frame;
- determining a region where is located an object of focus from the saliency map;
- modifying the depth map such that a range of depth values in the depth map that is associated with the object of focus is redistributed substantially centered about a depth level of a display screen;
- and
- generating a virtual stereoscopic image frame based on the modified depth map and the two-dimensional image frame.
A stereoscopic rendering system comprising:
- a memory;
- and
- a processing unit coupled with the memory, the processing unit being configured to:
- generate a saliency map of the two-dimensional image frame;
- determine a region where is located an object of focus from the saliency map;
- modify the depth map such that a range of depth values in the depth map that is associated with the object of focus is redistributed substantially centered about a depth level of a display screen;
- and
- generate a virtual stereoscopic image frame based on the modified depth map and the two-dimensional image frame.
A non-transitory computer readable medium storing a sequence of computer program instructions which, when executed by a processing unit, causes the processing unit to:
- generate a saliency map of the two-dimensional image frame;
- determine a region where is located an object of focus from the saliency map;
- modify the depth map such that a range of depth values in the depth map that is associated with the object of focus is redistributed substantially centered about a depth level of a display screen;
- and
- generate a virtual stereoscopic image frame based on the modified depth map and the two-dimensional image frame.
Dependencies are inferred from the claim text.