A Feature-Preserved Canonical Form for Non-rigid 3D Meshes

  title={A Feature-Preserved Canonical Form for Non-rigid 3D Meshes},
  author={Zhouhui Lian and Afzal Godil},
  journal={2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission},
Measuring the dissimilarity between non-rigid objects is a challenging problem in 3D shape retrieval. One potential solution is to construct the models' 3D canonical forms (i.e., isometry-invariant representations in 3D Euclidean space) on which any rigid shape matching algorithm can be applied. However, existing methods, which are typically based on embedding procedures, result in greatly distorted canonical forms, and thus could not provide satisfactory performance to distinguish non-rigid… CONTINUE READING


Publications citing this paper.
Showing 1-6 of 6 extracted citations


Publications referenced by this paper.
Showing 1-10 of 34 references

The Princeton Shape Benchmark

Proceedings Shape Modeling Applications, 2004. • 2004
View 6 Excerpts
Highly Influenced

On Bending Invariant Signatures for Surfaces

IEEE Trans. Pattern Anal. Mach. Intell. • 2003
View 7 Excerpts
Highly Influenced

Intrinsic spin images: A subspace decomposition approach to understanding 3d deformable shapes

X. Wang, Y. Liu, H. Zha
Proc. 3DPVT’10, pp. 17–20.
View 4 Excerpts
Highly Influenced

Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes

IEEE Trans. Pattern Anal. Mach. Intell. • 1999
View 6 Excerpts
Highly Influenced

Non-rigid 3D shape retrieval using Multidimensional Scaling and Bag-of-Features

2010 IEEE International Conference on Image Processing • 2010
View 1 Excerpt

Visual Similarity Based 3D Shape Retrieval Using Bag-of-Features

2010 Shape Modeling International Conference • 2010
View 6 Excerpts

Rectilinearity of 3D Meshes

International Journal of Computer Vision • 2009
View 1 Excerpt

Similar Papers

Loading similar papers…