Back to results
US 10,881,956 B2Granted
3D renderer to video encoder pipeline for improved visual quality and low latency
AssigneeIntel Corporation
InventorsTomasz Madajczak, Jason Tanner, Jill Boyce, Changliang Wang, Maciej Oleksy, James Varga, Jr.
Life of this patent
Estimating the term…
Abstract
Techniques related to the render and encode of graphics frames representative of 3D video games are discussed. Such techniques include translating one or more of a transparency map, a depth map, a color compression map, or a motion field used to encode a graphics frame to encode parameters and encoding the first graphics frame using the encode parameters to generate a bitstream.
Claims17
A system for coding rendered game content, comprising:
- memory to store a bitstream;
- and
- a processor coupled to the memory, the processor to:
- render a plurality graphics frames to encode,
- wherein the render of a first graphics frame of the plurality is based on one or more of a transparency map to blend two image layers into the first graphics frame, a depth map of the first graphics frame, a color compression map of the first graphics frame, or a motion field of the first graphics frame;
- translate one or more of the transparency map, the depth map, the color compression map, or the motion field to one or more encode parameters to encode the first graphics frame,
- wherein the encode parameters comprise a block partitioning policy map comprising a block partitioning policy for each of a plurality of blocks of the first graphics frame, and
- wherein the processor to translate comprises the processor to determine, for the blocks of the first graphics frame using the depth map, a static depth block measurement for each of the blocks and to compare each static depth block measurement to a threshold and populate the block partitioning policy map with an indicator to skip evaluation of one or more smaller partitions of the block when the static depth block measurement compares favorably to a threshold or an indicator to skip evaluation of at least one large partition of the block when the static depth block measurement compares unfavorably to the threshold;
- and
- encode the first graphics frame using the encode parameters to generate the bitstream.
7 more elements
A computer-implemented method for coding rendered game content, comprising:
- rendering a plurality graphics frames to encode,
- wherein the rendering of a first graphics frame of the plurality is based on one or more of a transparency map to blend two image layers into the first graphics frame, a depth map of the first graphics frame, a color compression map of the first graphics frame, or a motion field of the first graphics frame,
- translating one or more of the transparency map, the depth map, the color compression map, or the motion field to one or more encode parameters to encode the first graphics frame,
- wherein the encode parameters comprise a block partitioning policy map comprising a block partitioning policy for each of a plurality of blocks of the first graphics frame, and
- wherein said translating comprises
- determining, for the blocks of the first graphics frame using the depth map, a static depth block measurement for each of the blocks and
- comparing each static depth block measurement to a threshold and
- populating the block partitioning policy map with an indicator to skip evaluation of one or more smaller partitions of the block when the static depth block measurement compares favorably to a threshold or an indicator to skip evaluation of at least one large partition of the block when the static depth block measurement compares unfavorably to the threshold;
- and
- encoding the first graphics frame using the encode parameters to generate a bitstream.
7 more elements
At least one non-transitory machine readable medium comprising a plurality of instructions that, in response to being executed on a computing device, cause the computing device to code rendered game content by:
- rendering a plurality graphics frames to encode,
- wherein the rendering of a first graphics frame of the plurality is based on one or more of a transparency map to blend two image layers into the first graphics frame, a depth map of the first graphics frame, a color compression map of the first graphics frame, or a motion field of the first graphics frame;
- translating one or more of the transparency map, the depth map, the color compression map, or the motion field to one or more encode parameters to encode the first graphics frame,
- wherein the encode parameters comprise a block partitioning policy map comprising a block partitioning policy for each of a plurality of blocks of the first graphics frame, and
- wherein said translating comprises
- determining, for the blocks of the first graphics frame using the depth map, a static block measurement for each of the blocks and
- comparing each static depth block measurement to a threshold and
- populating the block partitioning policy map with an indicator to skip evaluation of one or more smaller partitions of the block when the static depth block measurement compares favorably to a threshold or an indicator to skip evaluation of at least one large partition of the block when the static depth block measurement compares unfavorably to the threshold;
- and
- encoding the first graphics frame using the encode parameters to generate a bitstream.
7 more elements
Dependencies are inferred from the claim text.