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

2018-05-01
Pickup, David
Liu, Juncheng
Sun, Xianfang
Rosin, Paul L.
Martin, Ralph R.
Cheng, Zhiquan
Lian, Zhouhui
Nie, Sipin
Jin, Longcun
Shamai, Gil
Sahillioğlu, Yusuf
Kavan, Ladislav
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.

Citation Formats
D. Pickup et al. , “An evaluation of canonical forms for non-rigid 3D shape retrieval,” GRAPHICAL MODELS, vol. 97, pp. 17–29, 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/38372.