Unsupervised Scale-Invariant Multispectral Shape Matching

12/19/2020
by   Idan Pazi, et al.
0

Alignment between non-rigid stretchable structures is one of the hardest tasks in computer vision, as the invariant properties are hard to define on one hand, and on the other hand no labelled data exists for real datasets. We present unsupervised neural network architecture based upon the spectrum of scale-invariant geometry. We build ontop the functional maps architecture, but show that learning local features, as done until now, is not enough once the isometric assumption breaks but can be solved using scale-invariant geometry. Our method is agnostic to local-scale deformations and shows superior performance for matching shapes from different domains when compared to existing spectral state-of-the-art solutions.

READ FULL TEXT

page 1

page 7

research
07/07/2022

Partial Shape Similarity via Alignment of Multi-Metric Hamiltonian Spectra

Evaluating the similarity of non-rigid shapes with significant partialit...
research
07/20/2022

Unsupervised Deep Multi-Shape Matching

3D shape matching is a long-standing problem in computer vision and comp...
research
12/10/2018

Unsupervised Deep Learning for Structured Shape Matching

We present a novel method for computing correspondences across shapes us...
research
12/29/2010

Affine-invariant diffusion geometry for the analysis of deformable 3D shapes

We introduce an (equi-)affine invariant diffusion geometry by which surf...
research
08/17/2023

Spatially and Spectrally Consistent Deep Functional Maps

Cycle consistency has long been exploited as a powerful prior for jointl...
research
10/12/2022

Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matching

In this work, we present a novel non-rigid shape matching framework base...
research
03/29/2023

Structured Epipolar Matcher for Local Feature Matching

Local feature matching is challenging due to the textureless and repetit...

Please sign up or login with your details

Forgot password? Click here to reset