Direkt zum Inhalt springen
Computer Vision & Artificial Intelligence
TUM School of Computation, Information and Technology
Technical University of Munich

Technical University of Munich

Menu

Links

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group SRL Group


Datasets


Please refer to the dedicated section of the Computer Vision Group website for datasets on Object Recognition and Segmentation and Non-rigid Shape Matching, comprehensive of ground-truth correspondences and labels.

Feel free to contact me personally if you need specific data from any of my publications.

Code


Consistent Matching of Shape Collections

This code implements the sparse cycle-consistent matching technique described in:

Consistent Partial Matching of Shape Collections via Sparse Modeling
L. Cosmo, E. Rodola, A. Albarelli, F. Memoli, and D. Cremers
Computer Graphics Forum, 2016

code (Matlab/C++)


Shape Matching Using Random Forests

This code implements the learning-based matching framework described in:

Dense Non-Rigid Shape Correspondence Using Random Forests
E. Rodola, S. Rota Bulo, T. Windheuser, M. Vestner, and D. Cremers
Proc. CVPR 2014

code (C++/Matlab)
Dataset (KIDS) (including ground-truth)


Consensus Segmentation of Deformable Shapes

This code implements the consensus segmentation / stable region detection technique for 3D meshes described in:

Robust Region Detection via Consensus Segmentation of Deformable Shapes
E. Rodola, S. Rota Bulo, and D. Cremers
Computer Graphics Forum, 33(5) (Proc. SGP 2014)

code (C++/Matlab)


Projection onto Elastic Net ball

This code implements the exact projection onto the elastic net ball of given convexity and radius in an efficient manner, and also includes a simple example of how to use elastic net constraints in a shape or graph matching problem, as detailed in the following paper:

Elastic Net Constraints for Shape Matching
E. Rodola, A. Torsello, T. Harada, Y. Kuniyoshi, and D. Cremers
2013 IEEE International Conference on Computer Vision (ICCV 2013)

code (C++/Matlab)


Multi-view Registration via Dual Quaternions

This demo code implements global error diffusion via dual quaternions in multi-view registration problems, as detailed in the following paper:

Multiview Registration via Graph Diffusion of Dual Quaternions
A. Torsello, E. Rodola, and A. Albarelli
2011 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2011)

code (C++)

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group SRL Group

Table of Contents