Dictionary learning for implicit neural compression

Dictionary learning for implicit neural compression addresses the challenge of efficient video coding by reconstructing and partitioning video data segments, leveraging INR parameters and dictionaries to enhance compression efficiency and reduce complexity.

WO2026087512A1PCT designated stage Publication Date: 2026-04-30INTERDIGITAL CE PATENT HOLDINGS SAS
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
PCT/EP2025/080341
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-10-21
Filing Date
2025-10-21
Publication Date
2026-04-30

AI Technical Summary

Technical Problem

Existing video coding systems face challenges in achieving efficient compression of digital video signals while maintaining high quality, particularly in leveraging spatial and temporal redundancies within video content.

Method used

The implementation of dictionary learning for implicit neural compression (INR) allows for the reconstruction and generation of dictionary-based INR parameters, enabling efficient compression by associating and partitioning segments of video data, and learning dictionaries based on loss functions to encode and decode video data effectively.

Benefits of technology

This approach achieves high compression efficiency with reduced computational complexity, effectively exploiting spatial and temporal redundancies in video content, resulting in improved video coding performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure EP2025080341_30042026_PF_FP_ABST
    Figure EP2025080341_30042026_PF_FP_ABST
Patent Text Reader

Abstract

Systems, methods, and instrumentalities are disclosed herein for dictionary learning for implicit neural compression (INR). In examples, a video decoder may decode an implicit neural representation (INR) parameter. An INR may be reconstructed based on the INR parameter. The decoder may compute a dictionary based on the reconstructed INR. A dictionary-based INR may be generated based on the computed dictionary. Data may be reconstructed based on the dictionary-based INR. In examples, the decoder may decode a training procedure used for the computation of the dictionary. The dictionary may be computed based (e.g., further based) on the training procedure. In examples, a video encoder may determine an INR parameter. The dictionary may be computed based on the INR parameter. The encoder may determine a dictionary-based INR parameter based on the computed dictionary. The INR parameter and the dictionary-based INR parameter may be encoded.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Image and video compression using learned dictionary of implicit neural representations

    WO2024078892A1

  • Coding unit based implicit neural representation (INR)

    WO2024184044A1