Energy information for neural network post filter
By integrating energy information into video bitstreams for neural network post-filters, the patent addresses the challenge of high energy consumption in video coding systems, enabling efficient and optimized use of these filters based on energy criteria.
Patent Information
- Application Number
- PCT/EP2025/067596
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-07-04
- Filing Date
- 2025-06-23
- Publication Date
- 2026-01-08
AI Technical Summary
Modern video coding systems face challenges in managing energy consumption, particularly with the introduction of neural-network post-filters, which can significantly increase energy requirements for processing and display, especially in consumer electronics.
Incorporating syntax elements in the video bitstream to provide energy information related to neural network post-processing filters, allowing decoders to make informed decisions about applying these filters based on energy criteria, such as energy consumption and savings.
Enables efficient management of energy usage by allowing decoders to selectively apply neural network post-filters, reducing overall energy consumption and optimizing performance based on device capabilities and user preferences.