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.
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
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.
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.
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.
Smart Images

Figure EP2025080341_30042026_PF_FP_ABST
Abstract
Citation Information
Patent Citations
Image and video compression using learned dictionary of implicit neural representations
WO2024078892A1
Coding unit based implicit neural representation (INR)
WO2024184044A1