Video Coding Post-Filter Signaling for Neural Network Strength Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video coding standards lack efficient methods for signaling neural network post-filter parameter information, which can enhance video quality but are not adequately integrated into current video coding frameworks.
Innovation Solution
Incorporating techniques for signaling neural network post-filter parameter information through syntax elements in the video coding process, allowing for the update and control of neural network post-filters, including filtering strength and auxiliary input data, to improve video decoding and display quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If existing video coding standards are used, then compatibility and ease of operation are maintained, but video quality enhancement through neural network post-filters cannot be achieved
Solution Approach 1:
The patent segments the neural network post-filter parameters into separate syntax elements that can be independently signaled in the bitstream. This allows the video coding system to maintain compatibility with existing standards while adding optional neural network filtering capabilities through discrete parameter signaling.
Solution Approach 2:
The patent introduces an intermediary layer between the video coding standard and neural network post-filter by defining specific syntax elements (nnf_filter_strength, nnf_auxiliary_input) that bridge the gap. These syntax elements act as mediators that carry neural network control information within the existing video bitstream structure.
2Manufacturing precision
If neural network post-filter parameters are added to video coding standards, then video quality is enhanced, but device complexity and standard complexity increase
Solution Approach 1:
The patent extracts the essential neural network post-filter control parameters (filter strength and auxiliary input data) as separate, minimal syntax elements. This extraction approach adds only the necessary complexity for neural network control without incorporating the full neural network processing complexity into the video coding standard.
Solution Approach 2:
The patent changes the parameter representation by using compact syntax elements (nnf_filter_strength with values 0-7, nnf_auxiliary_input with 0-1) to control neural network behavior. This parameterization approach simplifies the complexity by reducing continuous neural network parameters to discrete, efficiently coded values.
3Manufacturing precision
If comprehensive neural network post-filter control is implemented, then video decoding quality is improved, but loss of information and signaling overhead increase
Solution Approach 1:
The patent implements partial control of neural network post-filters by signaling only the most critical parameters (filter strength and auxiliary input presence). This partial action approach provides sufficient control for quality improvement while avoiding the excessive signaling overhead that would result from encoding complete neural network configurations.
Data Source
AI summary
A device may be configured to perform filtering based on information included in a neural network post-filter characteristics message. In one example, the neural network post-filter characteristics message includes a syntax element indicating auxiliary input data is present in an input tensor of the neural network post-filter. The device may derive a filtering strength control value array where each entry in the array is based on a quantization parameter of a respective input picture for the neural network post-filter.