A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding

TL;DR

This paper introduces a CNN-based post-processing method for HEVC video compression that significantly reduces artifacts and improves compression efficiency, outperforming previous neural network approaches in speed and memory usage.

Contribution

The paper presents a redesigned VRCNN tailored for HEVC post-processing, achieving higher bit-rate reduction and faster processing compared to existing CNN methods.

Findings

Average 4.6% bit-rate reduction with VRCNN

Outperforms previous networks in speed and memory efficiency

Achieves better artifact removal in HEVC videos

Abstract

Lossy image and video compression algorithms yield visually annoying artifacts including blocking, blurring, and ringing, especially at low bit-rates. To reduce these artifacts, post-processing techniques have been extensively studied. Recently, inspired by the great success of convolutional neural network (CNN) in computer vision, some researches were performed on adopting CNN in post-processing, mostly for JPEG compressed images. In this paper, we present a CNN-based post-processing algorithm for High Efficiency Video Coding (HEVC), the state-of-the-art video coding standard. We redesign a Variable-filter-size Residue-learning CNN (VRCNN) to improve the performance and to accelerate network training. Experimental results show that using our VRCNN as post-processing leads to on average 4.6% bit-rate reduction compared to HEVC baseline. The VRCNN outperforms previously studied networks in achieving higher bit-rate reduction, lower memory cost, and multiplied computational speedup.