Method and apparatus for block-wise neural image compression with post filtering

An apparatus for block-wise neural image compression with post filtering, the apparatus being implemented as an encoder, and the apparatus comprising:

• at least one memory configured to store program code;
• and
• at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
• first encoding code configured to cause the at least one processor to encode a block of an input image, using a first neural network, wherein the encoded block is decoded by a decoder using a second neural network to generate a reconstructed block;
• first performing code configured to cause the at least one processor to perform intra-prediction on the reconstructed block, using a third neural network, to generate a predicted block;
• determining code configured to cause the at least one processor to determine a difference between the block of the input image and the generated predicted block, to generate a prediction residual;
• second encoding code configured to cause the at least one processor to encode the generated prediction residual, using a fourth neural network, wherein the encoded prediction residual is decoded by the decoder using a fifth neural network;
• and
• adding code configured to cause the at least one processor to add the decoded prediction residual to the generated predicted block, to generate a recovered predicted block.

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor for block-wise neural image compression with post filtering of an encoder, cause the at least one processor to:

• encode a block of an input image, using a first neural network, wherein the encoded block is decoded by a decoder using a second neural network to generate a reconstructed block;
• perform intra-prediction on the reconstructed block, using a third neural network, to generate a predicted block;
• determine a difference between the block of the input image and the generated predicted block, to generate a prediction residual;
• encode the generated prediction residual, using a fourth neural network, wherein the encoded prediction residual is decoded by the decoder using a fifth neural network;
• and
• add the decoded prediction residual to the generated predicted block, to generate a recovered predicted block.