Unsupervised shape discovery using synchronized spectral networks

作者:

Highlights:

• A new unsupervised shape discovery method using a novel joint foreground/background segmentation and a dense part-part correspondence between all image pairs.

• A new multiscale spectral synchronization method which jointly align the spectral representations of all input images.

• A novel unsupervised superpixel-based groupwise co-registration which converts the implicit eigenvector-eigenvector synchronization to superpixel-superpixel dense correspondences.

摘要

•A new unsupervised shape discovery method using a novel joint foreground/background segmentation and a dense part-part correspondence between all image pairs.•A new multiscale spectral synchronization method which jointly align the spectral representations of all input images.•A novel unsupervised superpixel-based groupwise co-registration which converts the implicit eigenvector-eigenvector synchronization to superpixel-superpixel dense correspondences.

论文关键词:Spectral synchronization,Joint image matching,Groupwise segmentation,Shape discovery

论文评审过程:Received 19 June 2016, Revised 13 October 2016, Accepted 26 March 2017, Available online 3 April 2017, Version of Record 10 April 2017.

论文官网地址:https://doi.org/10.1016/j.patcog.2017.03.032