MapTree: Recovering Multiple Solutions in the Space of Maps

@article{Ren2020MapTreeRM,
  title={MapTree: Recovering Multiple Solutions in the Space of Maps},
  author={Jing Ren and S. Melzi and M. Ovsjanikov and Peter Wonka},
  journal={ACM Trans. Graph.},
  year={2020},
  volume={39},
  pages={264:1-264:17}
}
In this paper we propose an approach for computing multiple high-quality near-isometric maps between a pair of 3D shapes. Our method is fully automatic and does not rely on user-provided landmarks or descriptors. This allows us to analyze the full space of maps and extract multiple diverse and accurate solutions, rather than optimizing for a single optimal correspondence as done in previous approaches. To achieve this, we propose a compact tree structure based on the spectral map representation… Expand

References

SHOWING 1-10 OF 91 REFERENCES
Continuous and orientation-preserving correspondences via functional maps
Functional maps
Unsupervised Deep Learning for Structured Shape Matching
ZoomOut: Spectral Upsampling for Efficient Shape Correspondence
Consistent Shape Matching via Coupled Optimization
Point-wise Map Recovery and Refinement from Functional Correspondence
Blended intrinsic maps
Finding the M-best consistent correspondences between 3D symmetric objects
Informative Descriptor Preservation via Commutativity for Shape Matching
Entropic metric alignment for correspondence problems
...
1
2
3
4
5
...