In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds.
In this paper, we provide a theoretical foundation for pointwise map recovery from functional maps and highlight its relation to a range of shape correspondence methods based on spectral alignment.
Our attacks are universal, in that they transfer across different shapes, different representations (meshes and point clouds), and generalize to previously unseen data.
As a result, there exists a big performance gap between methods dealing with complete shapes, and methods that address missing geometry.
However, instead of using the Laplace-Beltrami eigenfunctions as done in virtually all previous works in this domain, we demonstrate that learning the basis from data can both improve robustness and lead to better accuracy in challenging settings.
This augmentation provides an effective workaround for the resolution limitations imposed by the adopted morphable model.
We propose a filtering feature selection framework that considers subsets of features as paths in a graph, where a node is a feature and an edge indicates pairwise (customizable) relations among features, dealing with relevance and redundancy principles.
We introduce the first learning-based method for recovering shapes from Laplacian spectra.
We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds.
Our main observation is that high quality maps can be obtained even if the input correspondences are noisy or are encoded by a small number of coefficients in a spectral basis.
This problem statement is similar to that of "biclustering", implying that RBC can be cast as a biclustering problem.
An appealing characteristic of the approach is that it aims to discover an abstraction behind low-level sensory data, that is, relevancy.
In an era where accumulating data is easy and storing it inexpensive, feature selection plays a central role in helping to reduce the high-dimensionality of huge amounts of otherwise meaningless data.
DFST proposes an optimized visual tracking algorithm based on the real-time selection of locally and temporally discriminative features.
Filter-based feature selection has become crucial in many classification settings, especially object recognition, recently faced with feature learning strategies that originate thousands of cues.