CPC G06T 3/4053 (2013.01) [G06F 18/2163 (2023.01); G06F 18/285 (2023.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06T 9/002 (2013.01); G06V 10/82 (2022.01)] | 18 Claims |
1. A method, comprising:
receiving a first texture block of a first block size;
generating coded-texture values in a compressed domain based on application of a first block compression (BC) scheme on the received first texture block;
applying a first machine learning model on the generated coded-texture values to generate super-resolution coded-texture values in the compressed domain; and
processing the generated super-resolution coded-texture values to generate a second texture block of a second block size, wherein the second block size is greater than the first block size, wherein the processing of the generated super-resolution coded-texture values comprises:
converting the super-resolution coded-texture values in the compressed domain to a first compressed bit-stream,
wherein
the first compressed bit-stream comprises a set of second blocks of coded-bits, and
each second block of coded-bits represents, in the compressed domain, a corresponding portion of the second texture block; and
decoding the first compressed bit-stream to generate the second texture block of the second block size.
|