Systems and methods for provisioning content
AssigneeFacebook, Inc.
InventorsEvgeny V. Kuzyakov, Renbin Peng, Chien-Nan Chen
Life of this patent
Estimating the term…
Abstract
Systems, methods, and non-transitory computer-readable media can provide at least one frame of a content item to a saliency prediction model, the saliency prediction model being trained to identify salient points of interest that appear in content items. Information describing at least a first salient point of interest that appears in the at least one frame can be obtained from the saliency prediction model. The first salient point of interest can be predicted to be of interest to users accessing the content item. A view-based projection can be applied to a region corresponding to the first salient point of interest, wherein the view-based projection enhances a quality in which the region is presented.
Claims21
(canceled)
A computer-implemented method comprising:
- generating, by a computing system, a spherical representation of a frame, the spherical representation including at least one point of interest;
- determining, by the computing system, a number of rays emanating from a virtual camera that are needed to capture a region of the frame, the region corresponding to the at least one point of interest;
- and
- based on the number of rays, allocating, by the computing system, a density of pixels to the region for presentation of the frame.
A system comprising:
- at least one processor;
- and
- a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:
- generating a spherical representation of a frame, the spherical representation including at least one point of interest;
- determining a number of rays emanating from a virtual camera that are needed to capture a region of the frame, the region corresponding to the at least one point of interest;
- and
- based on the number of rays, allocating a density of pixels to the region for presentation of the frame.
A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
- generating a spherical representation of a frame, the spherical representation including at least one point of interest;
- determining a number of rays emanating from a virtual camera that are needed to capture a region of the frame, the region corresponding to the at least one point of interest;
- and
- based on the number of rays, allocating a density of pixels to the region for presentation of the frame.
Dependencies are inferred from the claim text.