Patent · US Active

End-to-end deep generative network for low bitrate image coding

US12327385B2 · kind B2 · utility

0Cited by
3References
18Claims
0Family size

Assignees

Inventors

Key dates

Filing dateOct 19, 2022
Grant dateJun 10, 2025
Priority date
Expiry dateSep 28, 2043

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04N19/124
  • WIPO fieldAudio-visual technology
  • WIPO sectorElectrical engineering

Abstract

A neural network system, a method and an apparatus for image compression are provided. The neural network may include a generator including an encoder, an entropy estimator, and a decoder, where the encoder receives an input image and generates an encoder output, a plurality of quantized feature entries are obtained based on the encoder output outputted at a last encoder block, the entropy estimator receives the plurality of quantized feature entries and calculates an entropy loss based on the plurality of quantized feature entries, and the decoder receives the plurality of quantized feature entries and generates a reconstructed image. Furthermore, the neural network may include a discriminator that determines whether the reconstructed image different from the input image based on a discriminator loss. Moreover, the generator may determine whether content of the reconstructed image matches content of the input image based on a generator loss including the entropy loss.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.