Systems and methods for signaling patch size information for spatial extrapolation in video coding
AssigneeSharp Kabushiki Kaisha
InventorSachin G. Deshpande
Life of this patent
Estimating the term…
Abstract
A device may be configured to perform spatial extrapolation based on information included in a neural-network post-filter characteristics message. In one example, a neural-network post-filter characteristics message includes a syntax element indicating a purpose of the neural-network post-filter characteristics message is spatial extrapolation. In one example, a syntax element indicating overlapping horizontal and vertical sample counts and patch size related syntax elements are inferred based on a purpose being spatial extrapolation. In one example, a syntax element indicating overlapping horizontal and vertical sample counts and patch size related syntax elements are constrained based on a purpose being spatial extrapolation.
Claims3
A method of decoding video data, the method comprising:
- receiving a neural-network post-filter characteristics message;
- parsing a first syntax element in the neural-network post-filter characteristics message, wherein the first syntax element indicates a purpose of a neural-network post-filter and is defined to have a value that explicitly indicates that the neural-network post-filter has the purpose of spatial extrapolation;
- conditionally parsing a second syntax element and a third syntax element in the neural-network post-filter characteristics message only in cases where the first syntax element indicates the neural-network post-filter does not have the purpose of spatial extrapolation,
- wherein the second syntax element indicates overlapping horizontal and vertical sample counts of adjacent input tensors of the neural-network post-filter,
- wherein the third syntax element equal to 1 indicates that the neural-network post-filter accepts exactly an indicated patch size as input;
- inferring a value of the second syntax element to be equal to zero when it is not parsed;
- and
- inferring a value of the third syntax element to be equal to 1 when it is not parsed.
A device comprising one or more processors configured to:
- receive a neural-network post-filter characteristics message;
- parse a first syntax element in the neural-network post-filter characteristics message, wherein the first syntax element indicates a purpose of a neural-network post-filter and is defined to have a value that explicitly indicates that the neural-network post-filter has the purpose of spatial extrapolation;
- conditionally parse a second syntax element and a third syntax element in the neural-network post-filter characteristics message only in cases where the first syntax element indicates the neural-network post-filter does not have the purpose of spatial extrapolation,
- wherein the second syntax element indicates overlapping horizontal and vertical sample counts of adjacent input tensors of the neural-network post-filter,
- wherein the third syntax element equal to 1 indicates that the neural-network post- filter accepts exactly an indicated patch size as input;
- infer a value of the second syntax element to be equal to zero when it is not parsed;
- and
- infer a value of the third syntax element to be equal to 1 when it is not parsed.
Dependencies are inferred from the claim text.