CNN Video Filtering for Quantization Errors and Blocking Artifacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing data volume and complexity of video content, particularly in high-capacity games and 360-degree videos, necessitates a more efficient compression technique to reduce hardware resource consumption and mitigate quantization errors and blocking artifacts in video encoding and decoding processes.
Innovation Solution
Applying a convolutional neural network (CNN)-based filter to reconstructed video pictures, utilizing quantization parameter maps and block partition maps to enhance video decoding by mitigating quantization errors and blocking artifacts, and improving prediction accuracy through CNN-based intra- and inter-prediction methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If video data is compressed using traditional encoders, then hardware resource consumption is reduced, but quantization errors and blocking artifacts occur
Solution Approach 1:
The patent replaces traditional mechanical video filtering systems with an artificial neural network-based system. The neural network learns optimal filtering operations during training and applies learned patterns during decoding, substituting conventional signal processing algorithms with machine learning-based approaches that achieve better quality at comparable computational cost
Solution Approach 2:
The neural network is trained in advance on large datasets of video content to learn optimal filtering strategies for different compression scenarios. This preliminary training phase enables the network to automatically adapt to various quantization levels and block patterns without requiring real-time adjustment during actual video decoding
2Manufacturing precision
If video resolution and frame rate are increased, then video quality is improved, but data volume increases
Solution Approach 1:
The neural network dynamically adjusts filtering parameters based on the input video characteristics, including resolution, frame rate, and compression level. By learning optimal parameter settings from training data, the system achieves high-quality reconstruction of high-resolution video while maintaining efficient compression ratios
3Manufacturing precision
If CNN-based filter is applied to reduce quantization errors, then video quality is improved, but decoding complexity increases
Solution Approach 1:
The neural network weights and filtering parameters are pre-computed and stored during the training phase. During actual video decoding, the system applies these pre-learned filters rather than performing complex real-time optimization, effectively copying the learned solution to multiple video frames efficiently
Solution Approach 2:
The neural network processes video data in manageable segments corresponding to compression blocks, applying localized filtering operations to each block independently. This segmentation approach reduces overall computational complexity by breaking down the global optimization problem into smaller, parallelizable local problems
Data Source
AI summary
The present disclosure relates to video encoding or decoding and, more specifically, to an apparatus and a method for applying an artificial neural network (ANN) to video encoding or decoding. The apparatus and the method of the present disclosure are characterized by applying a CNN-based filter to a first picture and at least one of a quantization parameter map and a block partition map to output a second picture.