Published January 1, 2018 | Version v1
Journal article Open

An evaluation of canonical forms for non-rigid 3D shape retrieval

  • 1. Cardiff Univ, Cardiff, S Glam, Wales
  • 2. Avatar Sci Hunan Co, Changsha, Hunan, Peoples R China
  • 3. Peking Univ, Beijing, Peoples R China
  • 4. South China Univ Technol, Guangzhou, Guangdong, Peoples R China
  • 5. Technion Israel Inst Technol, Haifa, Israel
  • 6. Middle East Tech Univ, Ankara, Turkey
  • 7. Univ Utah, Salt Lake City, UT USA

Description

Canonical forms attempt to factor out a non-rigid shape's pose, giving a pose-neutral shape. This opens up the possibility of using methods originally designed for rigid shape retrieval for the task of non-rigid shape retrieval. We extend our recent benchmark for testing canonical form algorithms. Our new benchmark is used to evaluate a greater number of state-of-the-art canonical forms, on five recent non-rigid retrieval datasets, within two different retrieval frameworks. A total of fifteen different canonical form methods are compared. We find that the difference in retrieval accuracy between different canonical form methods is small, but varies significantly across different datasets. We also find that efficiency is the main difference between the methods.

Files

bib-dad71207-a351-4f57-a31e-255a8443515c.txt

Files (241 Bytes)

Name Size Download all
md5:b672df98c9a916c902126b33051fbf17
241 Bytes Preview Download