Video codec using deep learning model based on block
AssigneesHyundai Motor Company, Kia Corporation, Ewha University-Industry Collaboration Foundation
InventorsJe Won Kang, Seung Wook Park
Life of this patent
Estimating the term…
Abstract
A video decoding method includes: determining a motion vector of an input block included in a first picture; inter-predicting the input block using the motion vector of the input block to generate a prediction block for the input block; generating reconstructed samples for the input block based on the prediction block; obtaining reference sample values from a second picture reconstructed before the first picture; and filtering reconstructed samples for the input block by using the reference sample values obtained from the second picture.
Claims11
A video decoding method, comprising:
- determining a motion vector of an input block included in a first picture;
- inter-predicting the input block using the motion vector of the input block to generate a prediction block for the input block;
- generating reconstructed samples for the input block based on the prediction block;
- obtaining reference sample values from a second picture reconstructed before the first picture;
- and
- filtering reconstructed samples for the input block by using the reference sample values obtained from the second picture.
A video encoding method, comprising:
- determining a motion vector of an input block included in a first picture;
- inter-predicting the input block using the motion vector of the input block to generate a prediction block for the input block;
- generating reconstructed samples for the input block based on the prediction block;
- obtaining reference sample values from a second picture reconstructed before the first picture;
- and
- filtering reconstructed samples for the input block by using the reference sample values obtained from the second picture.
A method for providing video data to a video decoding apparatus, the method comprising:
- encoding the video data into a bitstream;
- and
- transmitting the bitstream to the video decoding apparatus,
- wherein encoding the video data comprises:
- determining a motion vector of an input block included in a first picture;
- inter-predicting the input block using the motion vector of the input block to generate a prediction block for the input block;
- generating reconstructed samples for the input block based on the prediction block;
- obtaining reference sample values from a second picture reconstructed before the first picture;
- and
- filtering reconstructed samples for the input block by using the reference sample values obtained from the second picture.
Dependencies are inferred from the claim text.