Model-Code Separation Architecture for Image Compression using Sum-Product Networks

According to some embodiments, a method of decoding data includes: receiving data compressed by a universal encoder and a data model based on a sum-product network (SPN) representing statistical structure inherent to source data, the source data corresponding to an uncompressed version of the data; and decompressing the data using the data model.

Researchers

Gregory Wornell / Tejas Jayashankar

Departments: Dept of Electrical Engineering & Computer Science
Technology Areas: Communication Systems: Optical / Computer Science: Networking & Signals
Impact Areas: Connected World

  • model-code separation architecture for image compression using sum-product networks
    United States of America | Pending

License this technology

Interested in this technology? Connect with our experienced licensing team to initiate the process.

Sign up for technology updates

Sign up now to receive the latest updates on cutting-edge technologies and innovations.