1

Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence With Functional Maps
In this paper, we provide a theoretical foundation for pointwise map recovery from functional maps and highlight its relation to a …
Cite URL GitHub
Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence With Functional Maps
Universal Spectral Adversarial Attacks for Deformable Shapes
Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong …
Cite URL PDF GitHub
Universal Spectral Adversarial Attacks for Deformable Shapes
Efficiently parallelizable strassen-based multiplication of a matrix by its transpose
An efficient algorithm for computing the multiplication of a matrix by its transpose, exploiting Strassen-like recursions. The algorithm is designed to be parallelized with multiple paradigms, from multi-threading to distributed computing.
Cite PDF GitHub
Efficiently parallelizable strassen-based multiplication of a matrix by its transpose
Intra-operative Update of Boundary Conditions for Patient-Specific Surgical Simulation
Patient-specific Biomechanical Models (PBMs) can enhance computer assisted surgical procedures with critical information. Although …
Cite
Intra-operative Update of Boundary Conditions for Patient-Specific Surgical Simulation
Orthogonalized Fourier polynomials for signal approximation and transfer
The usual Laplacian eigenbasis is extended to consider also polynomials of the eigenfunctions. The new extended basis has in increased descriptive power in signal reconstruction and transfer tasks, coming at a very reduced cost.
Cite PDF GitHub
Orthogonalized Fourier polynomials for signal approximation and transfer
Instant recovery of shape from spectrum via latent space connections
We introduce the first learning-based method for recovering shapes from Laplacian spectra. Given an auto-encoder, our model takes the …
Cite PDF GitHub Best Student Paper Award
Instant recovery of shape from spectrum via latent space connections
Towards Precise Completion of Deformable Shapes
According to Aristotle, the whole is greater than the sum of its parts. This statement was adopted to explain human perception by the …
Cite URL PDF
Towards Precise Completion of Deformable Shapes
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations
Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality …
Cite URL
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations
LIMP: Learning Latent Shape Representations with Metric Preservation Priors
In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D …
Cite arXiv GitHub
LIMP: Learning Latent Shape Representations with Metric Preservation Priors
Learning interaction patterns from surface representations of protein structure
Predicting interactions between proteins and other biomolecules purely based on structure is an unsolved problem in biology. The …
Cite URL PDF
Learning interaction patterns from surface representations of protein structure