Progressive Spatial Recurrent Neural Network for Intra Prediction

TL;DR

This paper introduces PS-RNN, a neural network-based intra prediction method for video coding that improves compression efficiency by reducing bit-rate while maintaining quality, especially for complex textures.

Contribution

The paper presents a novel Progressive Spatial Recurrent Neural Network for intra prediction, supporting variable block sizes and optimized with SATD loss for better rate-distortion performance.

Findings

Achieves 2.5% average bit-rate reduction compared to HEVC.

Supports variable block sizes for practical coding.

Outperforms traditional directional prediction methods.

Abstract

Intra prediction is an important component of modern video codecs, which is able to efficiently squeeze out the spatial redundancy in video frames. With preceding pixels as the context, traditional intra prediction schemes generate linear predictions based on several predefined directions (i.e. modes) for blocks to be encoded. However, these modes are relatively simple and their predictions may fail when facing blocks with complex textures, which leads to additional bits encoding the residue. In this paper, we design a Progressive Spatial Recurrent Neural Network (PS-RNN) that learns to conduct intra prediction. Specifically, our PS-RNN consists of three spatial recurrent units and progressively generates predictions by passing information along from preceding contents to blocks to be encoded. To make our network generate predictions considering both distortion and bit-rate, we propose to use Sum of Absolute Transformed Difference (SATD) as the loss function to train PS-RNN since SATD is able to measure rate-distortion cost of encoding a residue block. Moreover, our method supports variable-block-size for intra prediction, which is more practical in real coding conditions. The proposed intra prediction scheme achieves on average 2.5% bit-rate reduction on variable-block-size settings under the same reconstruction quality compared with HEVC.