Skip to content
This repository contains the implementation of my M.Sc. work "Partial Correspondence of 3D Shapes using Properties of the Nearest-Neighbor Field"
C++ MATLAB Mathematica C CMake Objective-C
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
FSPM
Faust_Sampling
Figures
Results
geodesic Release V0.9 Apr 13, 2019
nnf_sparse_code reorg results Apr 20, 2019
utils
visualization
.gitattributes Added result files Apr 16, 2019
.gitignore
DDIS_sparse_correspondences.m
README.md Added links to Paper,vide May 30, 2019
create_geo_matrices.m Helper tools Apr 13, 2019
runSHREC16A.m reorg results Apr 20, 2019
runSHREC16B.m
run_FAUST_test.m Release Apr 13, 2019
visualize_dense_matches.m reorg results Apr 20, 2019
visualize_sparse_matches.m Release Apr 13, 2019

README.md

Overview Results

Partial-Correspondence-3D-NNF

This repository contains the implementation of the work "Partial Correspondence of 3D Shapes using Properties of the Nearest-Neighbor Field" by Nadav Y. Arbel, Ayellet Tal and Lihi-Zelnik Manor. Video

The movement from sparse to dense correspondence has been done by adjusting to code of [1] which resides here to accept sparse correspondence

Installation Instructions

Made in windows 10

Prerequisites

  • PCL(1.8.1 64 bit MSVC 2017)
    • Might have to add VTK_DIR to environment variables : <PCL_intallation_folder>\3rdParty\VTK\lib\cmake\vtk­7.0
  • CMAKE
  • matlab
  • Visual Studio 2017 64 bit

Compilation

  1. Open cmake
  2. set source code directory to: <this_repository_root>\nnf_sparse_code\
  3. set build dir to <source_dir>\build\
  4. configure (with Visual Studio 15 2017 Win64) and generate
  5. click on open project
  6. in Visual Studio make sure branch is set to release and build 3DDIS_OMP

You now should be able to run everything in the root dir


Evaluation

We provide instructions to replicate our results. Sparse correspondences reside in "<match_dir>\refined_sparse", while dense correspondences reside in "<match_dir>\dense"

SHREC'16:PARTIAL MATCHING OF DEFORMABLE SHAPES[2]

To run this experiment please download the test set and evaluation code from their site.

Run runSHREC16A - just set the correct paths to the dataset inside the file.

For ground truth correspondences please contact the competition organizers, they had kindly provided me with the data, but had I have no permission to further divulge it myself.

Alternatively our obtained correspondences can be downloaded below.

Sparse, Dense

SHREC'16:Matching of Deformable Shapes with Topological Noise[3]

To run this experiment please download the low resolution test set and evaluation code from their site

Run runSHREC16B - just set the correct paths to the dataset inside the file.

Alternatively our obtained correspondences can be downloaded below.

Sparse, Dense

Here you need to provide geoedesic distance matrices for each model. I provide a matlab code which achieves this.

FAUST[4]

Download the dataset from the site.

Since we require sampling to make the problem tractable, and the dense correspondence algorithm[1] requires 2-manifold meshes of a specific area, you should copy the code from here into the model directory and run "run.bat"

Then run Run run_FAUST_test - just set the correct paths inside the file.

We have only made a qualitative evaluation here, as it contains full to part problems


Visualization

to visualizing correspondences we provide an example script for SHREC'16:Partial[1] one code is for sparse correspondences, and another for dense correspondences


References

[1]Litany O, Rodolà E, Bronstein AM, Bronstein MM. "Fully spectral partial shape matching." InComputer Graphics Forum 2017 May (Vol. 36, No. 2, pp. 247-258).

[2]Cosmo L, Rodolà E, Bronstein MM, Torsello A, Cremers D, Sahillioglu Y. "SHREC’16: Partial matching of deformable shapes." Proc. 3DOR. 2016;2(9):12.

[3]Lähner Z, Rodolà E, Bronstein MM, Cremers D, Burghard O, Cosmo L, Dieckmann A, Klein R, Sahillioglu Y. "SHREC’16: Matching of deformable shapes with topological noise." Proc. 3DOR. 2016 May 8;2:11.

[4]Bogo F, Romero J, Loper M, Black MJ. FAUST: Dataset and evaluation for 3D mesh registration. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2014 (pp. 3794-3801).

You can’t perform that action at this time.