公开(公告)号：US20250069270A1

公开(公告)日：2025-02-27

申请号：US18724026

申请日：2022-01-24

Applicant: Google LLC

Inventor： Joseph Johnson, Jr. ,  Shiblee Hasan ,  Emmanouil Koukoumidis ,  Dustin Abramson

IPC: G06T9/00 ,  G06T7/11 ,  G06V10/74

Abstract: A method includes obtaining image data, identifying a machine learning-compressible (ML-compressible) portion of the image data, and determining a location of the ML-compressible portion within the image data. The method also includes selecting, from a plurality of ML compression models, an ML compression model for the ML-compressible portion based on an image content thereof, and generating, based on the ML-compressible portion and by the ML compression model, an ML-compressed representation of the ML-compressible portion. The method further includes generating a compressed image data file that includes the ML-compressed representation and the location of the ML-compressible portion, and outputting the compressed image data file. The compressed image data file is configured to cause an ML decompression model corresponding to the ML compression model to generate a reconstruction of the ML-compressible portion of the image data based on the ML-compressed representation.