Fisher encoding of differential fast point feature histograms for partial 3D object retrieval

作者：

Highlights：

• First application of Fisher encoding in 3D object retrieval.

• The dFPFH extends FPFH, capturing more accurately local geometric transitions.

• The proposed similarity addresses partiality.

• The proposed method outperforms state-of-the-art in SHREC 2013 dataset.

• The proposed method outperforms state-of-the-art in cultural heritage datasets.

摘要

Highlights•First application of Fisher encoding in 3D object retrieval.•The dFPFH extends FPFH, capturing more accurately local geometric transitions.•The proposed similarity addresses partiality.•The proposed method outperforms state-of-the-art in SHREC 2013 dataset.•The proposed method outperforms state-of-the-art in cultural heritage datasets.

论文关键词：3D object retrieval,Partial matching,Local descriptors,Fisher encoding

论文评审过程：Received 20 April 2015, Revised 23 October 2015, Accepted 4 February 2016, Available online 12 February 2016, Version of Record 21 March 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.02.003