MV-GNN: Multi-View Graph Neural Network for Compression Artifacts Reduction

doi:10.1109/TIP.2020.2994412

MV-GNN: Multi-View Graph Neural Network for Compression Artifacts Reduction

2020-01-01

31

PRE

AI

DOI：10.1109/TIP.2020.2994412

Original

Original request for help

Save

Abstract

En 中文

Inevitable compression artifacts in multi-view video (MVV) can clearly degrade the quality of experience in many interaction-oriented 3D visual applications. Under the framework of asymmetric coding, low-quality images can be enhanced with high-quality images from the neighboring viewpoints considering the similarity among different views. However, compression artifacts and warping error cause different cross-view quality gaps for various sequences, and thus the contribution of cross-view priors can hardly be located and considered in previous works. In this paper, we propose a multi-view graph neural network (MV-GNN) to reduce compression artifacts in multi-view compressed images. We dedicate to design a fusion mechanism which can exploit contributions from neighboring viewpoints and meanwhile suppress the misleading information. In our method, a GNN-based fusion mechanism is designed to fuse the cross-view information under the aggregation and update mechanism of GNN. Experiments show that 1.672 dB and 0.0242 average gains on PSNR and SSIM metrics can be obtained, respectively. For the subjective evaluations, blocking effect in the compressed images are clearly suppressed and the damaged object boundary are better recovered. The experimental results demonstrate that our MV-GNN outperforms the state-of-the-art methods.

Keywords:

Image coding

Neural networks

Three-dimensional displays

Transform coding

Feature extraction

Image reconstruction

Visualization

Compression artifacts reduction

graph neural network

multi-view video compression

MV-GNN: Multi-View Graph Neural Network for Compression Artifacts Reduction

Abstract

AI Summary

Journal

Organization