US 12,262,060 B2
Systems and methods for signaling neural network post-filter patch size information in video coding
Sachin G. Deshpande, Camas, WA (US); and Ahmed Cheikh Sidiya, Morgantown, WV (US)
Assigned to Sharp Kabushiki Kaisha, Osaka (JP)
Filed by SHARP KABUSHIKI KAISHA, Osaka (JP)
Filed on Feb. 23, 2023, as Appl. No. 18/113,345.
Claims priority of provisional application 63/438,779, filed on Jan. 12, 2023.
Prior Publication US 2024/0244268 A1, Jul. 18, 2024
Int. Cl. H04N 19/80 (2014.01); H04N 19/70 (2014.01); H04N 19/85 (2014.01)
CPC H04N 19/80 (2014.11) [H04N 19/70 (2014.11); H04N 19/85 (2014.11)] 5 Claims
OG exemplary drawing
 
1. A method of performing neural network filtering for video data, the method comprising:
receiving a neural network post-filter characteristics message;
parsing a first syntax element from the neural network post-filter characteristics message indicating whether (i) a second syntax element and a third syntax element are present in the neural network post-filter characteristics message and a post-processing filter accepts a first patch size having a width equal to horizontal sample counts indicated by the second syntax element and a height equal to vertical sample counts indicated by the third syntax element, or (ii) a fourth syntax element and a fifth syntax element are present in the neural network post-filter characteristics message and the post-processing filter accepts a second patch size having a width equal to a multiple of horizontal sample counts indicated by the fourth syntax element and a height equal to a multiple of vertical sample counts indicated by the fifth syntax element; and
conditionally parsing the second syntax element and the third syntax element or the fourth syntax element and the fifth syntax element based on a value of the first syntax element.