US Patent Application 18320222. METHOD FOR CHROMA SUBSAMPLED FORMATS HANDLING IN MACHINE-LEARNING-BASED PICTURE CODING simplified abstract
METHOD FOR CHROMA SUBSAMPLED FORMATS HANDLING IN MACHINE-LEARNING-BASED PICTURE CODING
Organization Name
Inventor(s)
Elena Alexandrovna Alshina of Munich (DE)
METHOD FOR CHROMA SUBSAMPLED FORMATS HANDLING IN MACHINE-LEARNING-BASED PICTURE CODING - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18320222 Titled 'METHOD FOR CHROMA SUBSAMPLED FORMATS HANDLING IN MACHINE-LEARNING-BASED PICTURE CODING'
Simplified Explanation
The abstract describes a method for encoding and decoding video using machine learning. It specifically focuses on handling chroma subsampled formats, where the chroma component has a lower resolution than the luma component. To address this, the chroma component is up-sampled to match the resolution of the luma component before encoding. During decoding, the luma component and an intermediate chroma component are decoded from the bitstream, and the intermediate chroma component is then down-sampled to match the resolution of the luma component. This allows for the handling of sub-sampled chroma formats while preserving the luma channel.
Original Abstract Submitted
The present disclosure relates to video encoding and decoding, and in particular to handling of chroma subsampled formats in machine-learning-based video coding. Corresponding apparatuses and methods enable the processing for encoding and decoding of a respective picture portion that includes a luma component and a chroma component with a resolution lower than the luma component. In order to handle such different sized luma-chroma channels, the chroma component is up-sampled such that the obtained up-sampled chroma component has a resolution matching the one of the luma component. The luma and the up-sampled chroma component are then encoded into a bitstream. To reconstruct the picture portion, the luma component and an intermediate chroma component matching the resolution of the luma component are decoded from the bitstream, followed by down-sampling the intermediate chroma component. Thus, sub-sampled chroma formats may be handled by an autoencoder/autodecoder framework, while preserving the luma channel.
