Learning a referenceless stereopair quality engine with deep nonnegativity constrained sparse autoencoder

作者：

Highlights：

• A three-column deep non-negativity constrained sparse autoencoder is proposed for BSIQA.

• Both feature evolution and feature mapping are addressed in a unified framework for BSIQA.

• A Bayesian inference-based quality combination framework is used to derive 3D quality score.

摘要

•A three-column deep non-negativity constrained sparse autoencoder is proposed for BSIQA.•Both feature evolution and feature mapping are addressed in a unified framework for BSIQA.•A Bayesian inference-based quality combination framework is used to derive 3D quality score.

论文关键词：Image quality assessment,No-reference/referenceless,Stereoscopic 3D image,Deep learning,Nonnegativity constrained,Sparse autoencoder

论文评审过程：Received 15 March 2017, Revised 2 October 2017, Accepted 4 November 2017, Available online 7 November 2017, Version of Record 13 November 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.11.001