18455298. MEDIA COMPRESSION AND PROCESSING FOR MACHINE-LEARNING-BASED QUALITY METRICS (GOOGLE LLC)

MEDIA COMPRESSION AND PROCESSING FOR MACHINE-LEARNING-BASED QUALITY METRICS

Organization Name

GOOGLE LLC

Inventor(s)

Yao-Chung Lin of Sunnyvale CA (US)

Jingning Han of Santa Clara CA (US)

Yilin Wang of Sunnyvale CA (US)

Yeping Su of Palo Alto CA (US)

MEDIA COMPRESSION AND PROCESSING FOR MACHINE-LEARNING-BASED QUALITY METRICS

This abstract first appeared for US patent application 18455298 titled 'MEDIA COMPRESSION AND PROCESSING FOR MACHINE-LEARNING-BASED QUALITY METRICS

Original Abstract Submitted

Encoding using media compression and processing for machine-learning-based quality metrics includes generating encoded frame data by encoding a current frame from an input video using a neural-network-based video quality model, which includes identifying optimal encoding parameters for encoding a current block, wherein the optimal encoding parameters minimize a rate-distortion optimization cost function, which includes using a gradient value for the current block obtained from a neural-network-based video quality model generated gradient map obtained from the neural-network-based video quality model for the current frame, obtaining a restoration filtered reconstructed frame by restoration filtering a reconstructed frame, obtained by decoding the encoded frame data, using the neural-network-based video quality model generated gradient map obtained for the reconstructed frame.