Search Results - "Cosmo, Luca"

An Accurate and Robust Artificial Marker Based on Cyclic Codes by Bergamasco, Filippo, Albarelli, Andrea, Cosmo, Luca, Rodola, Emanuele, Torsello, Andrea

“…Artificial markers are successfully adopted to solve several vision tasks, ranging from tracking to calibration. While most designs share the same working…”
Get full text

High-Coverage 3D Scanning through Online Structured Light Calibration by Albarelli, Andrea, Cosmo, Luca, Bergamasco, Filippo, Torsello, Andrea

“…Many 3D scanning techniques rely on two or more well calibrated imaging cameras and a structured light source. Within these setups the light source does not…”
Get full text

Differentiable Graph Module (DGM) for Graph Convolutional Networks by Kazi, Anees, Cosmo, Luca, Ahmadi, Seyed-Ahmad, Navab, Nassir, Bronstein, Michael M.

“…Graph deep learning has recently emerged as a powerful ML concept allowing to generalize successful deep neural architectures to non-euclidean structured data…”
Get full text

GNN-LoFI: A novel graph neural network through localized feature-based histogram intersection by Bicciato, Alessandro, Cosmo, Luca, Minello, Giorgia, Rossi, Luca, Torsello, Andrea

“…Graph neural networks are increasingly becoming the framework of choice for graph-based machine learning. In this paper, we propose a new graph neural network…”
Get full text

3D Shape Analysis Through a Quantum Lens: the Average Mixing Kernel Signature by Cosmo, Luca, Minello, Giorgia, Bronstein, Michael, Rodolà, Emanuele, Rossi, Luca, Torsello, Andrea

“…The Average Mixing Kernel Signature is a novel spectral signature for points on non-rigid three-dimensional shapes. It is based on a quantum exploration…”
Get full text

Graph Kernel Neural Networks by Cosmo, Luca, Minello, Giorgia, Bicciato, Alessandro, Bronstein, Michael M., Rodola, Emanuele, Rossi, Luca, Torsello, Andrea

“…The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a…”
Get full text

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications by Zaripova, Kamilia, Cosmo, Luca, Kazi, Anees, Ahmadi, Seyed-Ahmad, Bronstein, Michael M., Navab, Nassir

“…Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are…”
Get full text

Learning Spectral Unions of Partial Deformable 3D Shapes by Moschella, Luca, Melzi, Simone, Cosmo, Luca, Maggioli, Filippo, Litany, Or, Ovsjanikov, Maks, Guibas, Leonidas, Rodolà, Emanuele

“…Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study of the Laplacian…”
Get full text

Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models by Postolache, Emilian, Mariani, Giorgio, Cosmo, Luca, Benetos, Emmanouil, Rodola, Emanuele

“…Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and…”
Get full text

Robust phase unwrapping by probabilistic consensus by Pistellato, Mara, Bergamasco, Filippo, Albarelli, Andrea, Cosmo, Luca, Gasparetto, Andrea, Torsello, Andrea

“…•Observed phase values can be represented as samples from a Normal Distribution.•The probabilistic approach offers a better accuracy when compared to other…”
Get full text

Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport by Saleh, Mahdi, Wu, Shun-Cheng, Cosmo, Luca, Navab, Nassir, Busam, Benjamin, Tombari, Federico

“…Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between…”
Get full text

An Information System for Brownfield Regeneration: providing customised information according to stakeholders' characteristics and needs by Rizzo, Erika, Pizzol, Lisa, Zabeo, Alex, Giubilato, Elisa, Critto, Andrea, Cosmo, Luca, Marcomini, Antonio

“…In the EU brownfield presence is still considered a widespread problem. Even though, in the last decades, many research projects and initiatives developed a…”
Get full text

Learning Spectral Unions of Partial Deformable 3D Shapes by Moschella, Luca, Melzi, Simone, Cosmo, Luca, Maggioli, Filippo, Litany, Or, Ovsjanikov, Maks, Guibas, Leonidas, Rodolà, Emanuele

“…Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study of the Laplacian…”
Get full text

Isospectralization, or How to Hear Shape, Style, and Correspondence by Cosmo, Luca, Panine, Mikhail, Rampini, Arianna, Ovsjanikov, Maks, Bronstein, Michael M., Rodola, Rodola

“…The question whether one can recover the shape of a geometric object from its Laplacian spectrum ('hear the shape of the drum') is a classical problem in…”
Get full text

Guided diffusion for inverse molecular design by Weiss, Tomer, Mayo Yanes, Eduardo, Chakraborty, Sabyasachi, Cosmo, Luca, Bronstein, Alex M, Gershoni-Poranne, Renana

“…The holy grail of materials science is de novo molecular design, meaning engineering molecules with desired characteristics. The introduction of generative…”
Get full text

Universal Spectral Adversarial Attacks for Deformable Shapes by Rampini, Arianna, Pestarini, Franco, Cosmo, Luca, Melzi, Simone, Rodola, Emanuele

“…Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong predictions despite being…”
Get full text

Phase-based spatio-temporal interpolation for accurate 3D localization in camera networks by Albarelli, Andrea, Cosmo, Luca, Bergamasco, Filippo, Sartoretto, Flavio

“…•We propose a general-purpose tracking device that can be used in several applications.•The design allows for an intrinsic time synchronization among tracking…”
Get full text

Parameter-Free Lens Distortion Calibration of Central Cameras by Bergamasco, Filippo, Cosmo, Luca, Gasparetto, Andrea, Albarelli, Andrea, Torsello, Andrea

“…At the core of many Computer Vision applications stands the need to define a mathematical model describing the imaging process. To this end, the pinhole model…”
Get full text

Adaptive Albedo Compensation for Accurate Phase-Shift Coding by Pistellato, Mara, Cosmo, Luca, Bergamasco, Filippo, Gasparetto, Andrea, Albarelli, Andrea

“…Among structured light strategies, the ones based on phase shift are considered to be the most adaptive with respect to the features of the objects to be…”
Get full text

Cross-Dataset Data Augmentation for Convolutional Neural Networks Training by Gasparetto, Andrea, Ressi, Dalila, Bergamasco, Filippo, Pistellato, Mara, Cosmo, Luca, Boschetti, Marco, Ursella, Enrico, Albarelli, Andrea

“…Within modern Deep Learning setups, data augmentation is the weapon of choice when dealing with narrow datasets or with a poor range of different samples…”
Get full text