Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Smooth Shells: Multi-Scale Shape Registration with Functional Maps

About

We propose a novel 3D shape correspondence method based on the iterative alignment of so-called smooth shells. Smooth shells define a series of coarse-to-fine shape approximations designed to work well with multiscale algorithms. The main idea is to first align rough approximations of the geometry and then add more and more details to refine the correspondence. We fuse classical shape registration with Functional Maps by embedding the input shapes into an intrinsic-extrinsic product space. Moreover, we disambiguate intrinsic symmetries by applying a surrogate based Markov chain Monte Carlo initialization. Our method naturally handles various types of noise that commonly occur in real scans, like non-isometry or incompatible meshing. Finally, we demonstrate state-of-the-art quantitative results on several datasets and show that our pipeline produces smoother, more realistic results than other automatic matching methods in real world applications.

Marvin Eisenberger, Zorah L\"ahner, Daniel Cremers• 2019

Related benchmarks

TaskDatasetResultRank
Shape MatchingFAUST (test)
Mean Geodesic Error0.025
88
3D shape matchingFAUST Anisotropic (F_a)
Mean Geodesic Error0.054
66
3D shape matchingSCAPE Anisotropic (S_a)
Mean Geodesic Error (x100)5
66
3D Shape CorrespondenceFAUST remeshed (test)
Mean Geodesic Error (x100)2.5
65
Non-isometric 3D shape matchingSMAL
Mean Geodesic Error0.361
58
Shape correspondence estimationTOPKIDS
Geodesic Error (x100)10.8
55
Shape CorrespondenceSCAPE (test)
Shape Correspondence Error0.047
54
Shape MatchingSCAPE remeshed (test)
Mean Geodesic Error (x100)4.7
46
Near-isometric shape matchingSCAPE (test)
Mean Geodesic Error0.047
42
3D Shape CorrespondenceFAUST_r (test)
Mean Geodesic Error (x100)2.5
37
Showing 10 of 41 rows

Other info

Follow for update