Image encoder using machine learning and data processing method of the image encoder

A method for processing image data, the method comprising:

• generating a prediction block from time-domain data of a previous input block;
• transforming the prediction block into an enhanced prediction block by applying at least one of a plurality of machine learning techniques to the prediction block;
• and
• generating a residual block by subtracting the enhanced prediction block from a current input block,
• wherein the generating the prediction block further comprises:
• generating a first prediction block based on the previous input block;
• obtaining a motion vector representing an offset between the current input block and a reference block, wherein the reference block is a block most closely matched with the current input block within in a reference image;
• generating a second prediction block by performing a motion compensation using the motion vector;
• and
• determining one of the first prediction block or the second prediction block as the prediction block.

An image encoder for outputting a bitstream by encoding an input image, the image encoder comprising:

• a predictive block configured to generate a prediction block using data of a previous input block;
• a machine learning based prediction enhancement (MLBE) block configured to transform the prediction block into an enhanced prediction block by applying a machine learning technique to the prediction block, wherein the MLBE block:
• selects one of the prediction block and the enhanced prediction block as a selected block in response to a rate-distortion optimization (RDO) value, wherein the enhanced prediction block is selected as the selected block in response to a rate-distortion optimization (RDO) value corresponding to the enhanced prediction block indicating a performance gain with respect to an RDO value corresponding to the prediction block, and the prediction block is selected as the selected block in response to the RDO value corresponding to the enhanced prediction block indicating no performance gain with respect to the RDO value corresponding to the prediction block,
• a coder controller configured to determine partitioning, coding, and decoding of the input image;
• and
• a subtractor configured to generate a residual block of residual data by subtracting pixel data of the selected block from pixel data of a current input block,0
• wherein the predictive block comprises:
• an intra prediction block configured to generate a first prediction block based on the previous input block;
• a motion estimation block configured to obtain a motion vector representing an offset between the current input block and a reference block, wherein the reference block is a block most closely matched with the current input block within in a reference image;
• a motion compensation block configured to generate a second prediction block by performing a motion compensation using the motion vector;
• and
• a mode decision block configured to determine one of the first prediction block or the second prediction block as the prediction block.