Modeling spatial layout for scene image understanding via a novel multiscale sum-product network

作者：

Highlights：

• A new deep architecture MSPN is proposed for image segmentation.

• Multiscale unary potentials are used to model image spatial layouts.

• A superpixel-based refinement method is used to improve the parsing results.

摘要

•A new deep architecture MSPN is proposed for image segmentation.•Multiscale unary potentials are used to model image spatial layouts.•A superpixel-based refinement method is used to improve the parsing results.

论文关键词：Scene image understanding,Spatial layout,Multiscale unary potentials,Multiscale sum-product network,MSPN

论文评审过程：Received 19 January 2016, Revised 8 July 2016, Accepted 9 July 2016, Available online 12 July 2016, Version of Record 15 July 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.07.015