Search Results for author: Simone Melzi

Found 18 papers, 7 papers with code

Learning to generate shape from global-local spectra

no code implementations4 Aug 2021 Marco Pegoraro, Riccardo Marin, Simone Melzi, Emanuele Rodolà, Umberto Castellani

In this work, we present a new learning-based pipeline for the generation of 3D shapes.

Shape registration in the time of transformers

1 code implementation25 Jun 2021 Giovanni Trappolini, Luca Cosmo, Luca Moschella, Riccardo Marin, Simone Melzi, Emanuele Rodolà

In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds.

Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence With Functional Maps

no code implementations CVPR 2021 Gautam Pai, Jing Ren, Simone Melzi, Peter Wonka, Maks Ovsjanikov

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.

Universal Spectral Adversarial Attacks for Deformable Shapes

no code implementations CVPR 2021 Arianna Rampini, Franco Pestarini, Luca Cosmo, Simone Melzi, Emanuele Rodolà

Our attacks are universal, in that they transfer across different shapes, different representations (meshes and point clouds), and generalize to previously unseen data.

Spectral Unions of Partial Deformable 3D Shapes

no code implementations31 Mar 2021 Luca Moschella, Simone Melzi, Luca Cosmo, Filippo Maggioli, Or Litany, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà

As a result, there exists a big performance gap between methods dealing with complete shapes, and methods that address missing geometry.

Learning disentangled representations via product manifold projection

no code implementations2 Mar 2021 Marco Fumero, Luca Cosmo, Simone Melzi, Emanuele Rodolà

We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations.

Correspondence Learning via Linearly-invariant Embedding

1 code implementation NeurIPS 2020 Riccardo Marin, Marie-Julie Rakotosaona, Simone Melzi, Maks Ovsjanikov

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.

High-Resolution Augmentation for Automatic Template-Based Matching of Human Models

no code implementations19 Sep 2020 Riccardo Marin, Simone Melzi, Emanuele Rodolà, Umberto Castellani

This augmentation provides an effective workaround for the resolution limitations imposed by the adopted morphable model.

Infinite Feature Selection: A Graph-based Feature Filtering Approach

1 code implementation15 Jun 2020 Giorgio Roffo, Simone Melzi, Umberto Castellani, Alessandro Vinciarelli, Marco Cristani

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.

Feature Selection

ZoomOut: Spectral Upsampling for Efficient Shape Correspondence

2 code implementations16 Apr 2019 Simone Melzi, Jing Ren, Emanuele Rodolà, Abhishek Sharma, Peter Wonka, Maks Ovsjanikov

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.

Graphics

Ranking to Learn: Feature Ranking and Selection via Eigenvector Centrality

no code implementations18 Apr 2017 Giorgio Roffo, Simone Melzi

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.

Feature Selection Object Recognition

Object Tracking via Dynamic Feature Selection Processes

no code implementations7 Sep 2016 Giorgio Roffo, Simone Melzi

DFST proposes an optimized visual tracking algorithm based on the real-time selection of locally and temporally discriminative features.

Feature Selection Object Tracking +1

Infinite Feature Selection

1 code implementation ICCV 2015 Giorgio Roffo, Simone Melzi, Marco Cristani

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.

Classification Feature Selection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.