Unsupervised Scale-Invariant Multispectral Shape Matching
This work tackles the problem of aligning non-rigid stretchable structures, which is a challenging task in computer vision due to the difficulty in defining invariant properties and the lack of labeled data.
The paper addresses the challenge of aligning non-rigid, stretchable structures without labeled data by proposing an unsupervised neural network architecture. This method leverages multiple scale-invariant geometries in the spectral domain to achieve superior performance in matching shapes from different domains compared to existing spectral state-of-the-art solutions.
Alignment between non-rigid stretchable structures is one of the most challenging tasks in computer vision, as the invariant properties are hard to define, and there is no labeled data for real datasets. We present unsupervised neural network architecture based upon the spectral domain of scale-invariant geometry. We build on top of the functional maps architecture, but show that learning local features, as done until now, is not enough once the isometry assumption breaks. We demonstrate the use of multiple scale-invariant geometries for solving this problem. 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.