Dual Geometric Graph Network (DG2N) – Zero-Shot Refinement for Dense Shape Correspondence

11/30/2020
by   Dvir Ginzburg, et al.
0

We provide a novel new approach for aligning geometric models using a dual graph structure where local features are mapping probabilities. Alignment of non-rigid structures is one of the most challenging computer vision tasks due to the high number of unknowns needed to model the correspondence. We have seen a leap forward using DNN models in template alignment and functional maps, but those methods fail for inter-class alignment where nonisometric deformations exist. Here we propose to rethink this task and use unrolling concepts on a dual graph structure - one for a forward map and one for a backward map, where the features are pulled back matching probabilities from the target into the source. We report state of the art results on stretchable domains alignment in a rapid and stable solution for meshes and cloud of points.

READ FULL TEXT

page 1

page 3

page 12

research
06/05/2023

Zero-Shot 3D Shape Correspondence

We propose a novel zero-shot approach to computing correspondences betwe...
research
03/15/2023

Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement

Template matching is a fundamental task in computer vision and has been ...
research
12/03/2019

Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes

We present the first utterly self-supervised network for dense correspon...
research
07/13/2018

Learning-based Natural Geometric Matching with Homography Prior

Geometric matching is a key step in computer vision tasks. Previous lear...
research
01/14/2023

NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching

We present Neural Correspondence Prior (NCP), a new paradigm for computi...
research
06/14/2019

Correspondence-Free Region Localization for Partial Shape Similarity via Hamiltonian Spectrum Alignment

We consider the problem of localizing relevant subsets of non-rigid geom...
research
04/06/2021

Sparse Partial Least Squares for Coarse Noisy Graph Alignment

Graph signal processing (GSP) provides a powerful framework for analyzin...

Please sign up or login with your details

Forgot password? Click here to reset