Deep point-to-subspace metric learning for sketch-based 3D shape retrieval

作者：

Highlights：

• A representative-view selection (RVS) module is designed to identify the most representative views of a 3D shape for reducing the redundancy.

• A deep point-to-subspace metric learning (DPSML) module is proposed to calculate the query-adaptive similarity for sketch-based 3D shape retrieval.

• The representation learning problem is formulated as a classification problem with a specially designed classifier and training loss.

• State-of-the-art performance on SHREC 2013, 2014 and 2016 benchmarks are achieved.

摘要

•A representative-view selection (RVS) module is designed to identify the most representative views of a 3D shape for reducing the redundancy.•A deep point-to-subspace metric learning (DPSML) module is proposed to calculate the query-adaptive similarity for sketch-based 3D shape retrieval.•The representation learning problem is formulated as a classification problem with a specially designed classifier and training loss.•State-of-the-art performance on SHREC 2013, 2014 and 2016 benchmarks are achieved.

论文关键词：Sketch-based 3D shape retrieval,Cross-modality discrepancy,Representative-view selection,Point-to-subspace distance

论文评审过程：Received 28 January 2019, Revised 27 June 2019, Accepted 21 July 2019, Available online 22 July 2019, Version of Record 30 July 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.106981