Context-adaptive neural network based prediction for image compression

TL;DR

This paper introduces a set of neural network architectures for intra image prediction in compression, which adapt to block size and texture complexity, improving PSNR-rate performance over prior methods.

Contribution

The paper proposes PNNS, a flexible neural network set that adapts to block size and texture, enhancing image compression performance without needing to signal the network choice.

Findings

PSNR-rate gains of 1.46% to 5.20% when integrated into H.265.

PNNS outperforms prior neural network methods by an average of 0.99%.

PNNS models a wide range of complex textures effectively.

Abstract

This paper describes a set of neural network architectures, called Prediction Neural Networks Set (PNNS), based on both fully-connected and convolutional neural networks, for intra image prediction. The choice of neural network for predicting a given image block depends on the block size, hence does not need to be signalled to the decoder. It is shown that, while fully-connected neural networks give good performance for small block sizes, convolutional neural networks provide better predictions in large blocks with complex textures. Thanks to the use of masks of random sizes during training, the neural networks of PNNS well adapt to the available context that may vary, depending on the position of the image block to be predicted. When integrating PNNS into a H.265 codec, PSNR-rate performance gains going from 1.46% to 5.20% are obtained. These gains are on average 0.99% larger than those of prior neural network based methods. Unlike the H.265 intra prediction modes, which are each specialized in predicting a specific texture, the proposed PNNS can model a large set of complex textures.