IP Library Granted Patent US 12666066
Granted Patent B2
US 12666066 · App. 18/763,912 · Granted Jun 23, 2026

Devices and methods for signaling multiple extrapolations in video coding via a neural-network post-filter characteristics supplemental enhancement information message

Inventor: Sachin G. Deshpande (Vancouver, WA)
Assignee: Sharp Kabushiki Kaisha
H04N19/44H04N19/70
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12666066
App. No.
18/763,912
Granted
Jun 23, 2026
Kind
B2
Abstract

A device may be configured to perform spatial or temporal 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 a neural-network post-filter. In one example, a syntax element indicating a number of extrapolations is included in the neural-network post-filter characteristics message based on whether a purpose is spatial extrapolation or temporal extrapolation.

Claims (15)

1 . A method of decoding video data, the method comprising:

receiving a neural-network post-filter characteristics supplemental enhancement information (SEI) message;

parsing a first syntax element in the neural-network post-filter characteristics supplemental enhancement information (SEI) message, wherein the first syntax element indicates a purpose of a neural-network post-filter is temporal extrapolation;

parsing a second syntax element in the neural-network post-filter characteristics supplemental enhancement information (SEI) message, wherein the second syntax element plus one specifies a number of extrapolated pictures generated by the neural-network post-filter subsequent to all input pictures for the neural-network post-filter in output order; and

parsing a third syntax element in the neural-network post-filter characteristics supplemental enhancement information (SEI) message, wherein the third syntax element plus one indicates a number of alternative temporal extrapolations generated by the neural-network post.

2 . A video decoder comprising one or more processors configured to:

receive a neural-network post-filter characteristics supplemental enhancement information (SEI) message;

parse a first syntax element in the neural-network post-filter characteristics supplemental enhancement information (SEI) message, wherein the first syntax element indicates a purpose of a neural-network post-filter is temporal extrapolation;

parse a second syntax element in the neural-network post-filter characteristics supplemental enhancement information (SEI) message, wherein the second syntax element plus one specifies a number of extrapolated pictures generated by the neural-network post-filter subsequent to all input pictures for the neural-network post-filter in output order; and

parse a third syntax element in the neural-network post-filter characteristics supplemental enhancement information (SEI) message, wherein the third syntax element plus one indicates a number of alternative temporal extrapolations generated by the neural-network post-filter.

3 . A device comprising one or more processors configured to:

signal a neural-network post-filter characteristics supplemental enhancement information (SEI) message, wherein the neural-network post-filter characteristics supplemental enhancement information (SEI) message includes:

a first syntax element, wherein the first syntax element indicates a purpose of a neural-network post-filter is temporal extrapolation,

a second syntax element, wherein the second syntax element plus one specifies a number of extrapolated pictures generated by the neural-network post-filter subsequent to all input pictures for the neural-network post-filter in output order, and

a third syntax element, wherein the third syntax element plus one indicates a number of alternative temporal extrapolations generated by the neural-network post-filter.