Supervoxel classification forests for estimating pairwise image correspondences

作者：

Highlights：

• A method for using random forests to estimate image correspondences is proposed.

• The method does not rely on the availability of manual label annotations.

• Labels for training are obtained via the use of supervoxels.

• The efficient method is effective at providing an estimate of image correspondences.

摘要

•A method for using random forests to estimate image correspondences is proposed.•The method does not rely on the availability of manual label annotations.•Labels for training are obtained via the use of supervoxels.•The efficient method is effective at providing an estimate of image correspondences.

论文关键词：Random forests,Unsupervised learning,Image correspondences,Supervoxels

论文评审过程：Received 31 January 2016, Revised 9 June 2016, Accepted 21 September 2016, Available online 22 September 2016, Version of Record 27 November 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.09.026