Dual Learning-based Video Coding with Inception Dense Blocks

TL;DR

This paper introduces a dual learning-based intra coding method for video compression that combines different neural network structures for prediction and filtering, achieving state-of-the-art performance and significant bitrate savings.

Contribution

First to combine two different neural network architectures in intra coding, enhancing prediction and filtering for improved video compression performance.

Findings

Achieved 10.24% BD-rate reduction on PCS sequences.

Achieved 9.70% BD-rate reduction on HEVC sequences.

First to integrate dual networks in intra coding for video compression.

Abstract

In this paper, a dual learning-based method in intra coding is introduced for PCS Grand Challenge. This method is mainly composed of two parts: intra prediction and reconstruction filtering. They use different network structures, the neural network-based intra prediction uses the full-connected network to predict the block while the neural network-based reconstruction filtering utilizes the convolutional networks. Different with the previous filtering works, we use a network with more powerful feature extraction capabilities in our reconstruction filtering network. And the filtering unit is the block-level so as to achieve a more accurate filtering compensation. To our best knowledge, among all the learning-based methods, this is the first attempt to combine two different networks in one application, and we achieve the state-of-the-art performance for AI configuration on the HEVC Test sequences. The experimental result shows that our method leads to significant BD-rate saving for provided 8 sequences compared to HM-16.20 baseline (average 10.24% and 3.57% bitrate reductions for all-intra and random-access coding, respectively). For HEVC test sequences, our model also achieved a 9.70% BD-rate saving compared to HM-16.20 baseline for all-intra configuration.