Search Results for author: Emanuele Rodolà

Found 56 papers, 32 papers with code

Towards Precise Completion of Deformable Shapes

1 code implementation ECCV 2020 Oshri Halimi, Ido Imanuel, Or Litany, Giovanni Trappolini, Emanuele Rodolà, Leonidas Guibas, Ron Kimmel

Here, we claim that observing part of an object which was previously acquired as a whole, one could deal with both partial matching and shape completion in a holistic manner.


Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models

1 code implementation18 Mar 2024 Emilian Postolache, Giorgio Mariani, Luca Cosmo, Emmanouil Benetos, Emanuele Rodolà

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation.

Zero-Shot Duet Singing Voices Separation with Diffusion Models

1 code implementation13 Nov 2023 Chin-Yun Yu, Emilian Postolache, Emanuele Rodolà, György Fazekas

In this paper, we examine this problem in the context of duet singing voices separation, and propose a method to enforce the coherency of singer identity by splitting the mixture into overlapping segments and performing posterior sampling in an auto-regressive manner, conditioning on the previous segment.

From Charts to Atlas: Merging Latent Spaces into One

no code implementations11 Nov 2023 Donato Crisostomi, Irene Cannistraci, Luca Moschella, Pietro Barbiero, Marco Ciccone, Pietro Liò, Emanuele Rodolà

Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces.

Latent Space Translation via Semantic Alignment

1 code implementation NeurIPS 2023 Valentino Maiorca, Luca Moschella, Antonio Norelli, Marco Fumero, Francesco Locatello, Emanuele Rodolà

While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible.


SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis

no code implementations23 Oct 2023 Marco Comunità, Riccardo F. Gramaccioni, Emilian Postolache, Emanuele Rodolà, Danilo Comminiello, Joshua D. Reiss

Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and virtual/augmented reality.

From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication

no code implementations2 Oct 2023 Irene Cannistraci, Luca Moschella, Marco Fumero, Valentino Maiorca, Emanuele Rodolà

It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases.

Camoscio: an Italian Instruction-tuned LLaMA

1 code implementation31 Jul 2023 Andrea Santilli, Emanuele Rodolà

In recent years Large Language Models (LLMs) have increased the state of the art on several natural language processing tasks.

Language Modelling

Vector Quantile Regression on Manifolds

1 code implementation3 Jul 2023 Marco Pegoraro, Sanketh Vedula, Aviv A. Rosenberg, Irene Tallini, Emanuele Rodolà, Alex M. Bronstein

Quantile regression (QR) is a statistical tool for distribution-free estimation of conditional quantiles of a target variable given explanatory features.


Geometric Epitope and Paratope Prediction

no code implementations28 May 2023 Marco Pegoraro, Clémentine Dominé, Emanuele Rodolà, Petar Veličković, Andreea Deac

Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules.

Accelerating Transformer Inference for Translation via Parallel Decoding

3 code implementations17 May 2023 Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, Emanuele Rodolà

We propose to reframe the standard greedy autoregressive decoding of MT with a parallel formulation leveraging Jacobi and Gauss-Seidel fixed-point iteration methods for fast inference.

Machine Translation Translation

Multimodal Neural Databases

1 code implementation2 May 2023 Giovanni Trappolini, Andrea Santilli, Emanuele Rodolà, Alon Halevy, Fabrizio Silvestri

The rise in loosely-structured data available through text, images, and other modalities has called for new ways of querying them.

Information Retrieval Multimodal Deep Learning +1

Fluid Dynamics Network: Topology-Agnostic 4D Reconstruction via Fluid Dynamics Priors

no code implementations17 Mar 2023 Daniele Baieri, Stefano Esposito, Filippo Maggioli, Emanuele Rodolà

Representing 3D surfaces as level sets of continuous functions over $\mathbb{R}^3$ is the common denominator of neural implicit representations, which recently enabled remarkable progress in geometric deep learning and computer vision tasks.

4D reconstruction

Bootstrapping Parallel Anchors for Relative Representations

1 code implementation1 Mar 2023 Irene Cannistraci, Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Emanuele Rodolà

The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applications.

Semantic correspondence

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

1 code implementation4 Feb 2023 Giorgio Mariani, Irene Tallini, Emilian Postolache, Michele Mancusi, Luca Cosmo, Emanuele Rodolà

In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources sharing a context.

Imputation Music Generation

Latent Spectral Regularization for Continual Learning

1 code implementation9 Jan 2023 Emanuele Frascaroli, Riccardo Benaglia, Matteo Boschini, Luca Moschella, Cosimo Fiorini, Emanuele Rodolà, Simone Calderara

While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing training data distribution.

Continual Learning

Latent Autoregressive Source Separation

1 code implementation9 Jan 2023 Emilian Postolache, Giorgio Mariani, Michele Mancusi, Andrea Santilli, Luca Cosmo, Emanuele Rodolà

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance.

Dimensionality Reduction

Relative representations enable zero-shot latent space communication

no code implementations30 Sep 2022 Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, Emanuele Rodolà

Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations.

Sparse Vicious Attacks on Graph Neural Networks

1 code implementation20 Sep 2022 Giovanni Trappolini, Valentino Maiorca, Silvio Severino, Emanuele Rodolà, Fabrizio Silvestri, Gabriele Tolomei

In this work, we focus on a specific, white-box attack to GNN-based link prediction models, where a malicious node aims to appear in the list of recommended nodes for a given target victim.

Link Prediction Recommendation Systems

KiloNeuS: A Versatile Neural Implicit Surface Representation for Real-Time Rendering

no code implementations22 Jun 2022 Stefano Esposito, Daniele Baieri, Stefan Zellmann, André Hinkenjann, Emanuele Rodolà

NeRF-based techniques fit wide and deep multi-layer perceptrons (MLPs) to a continuous radiance field that can be rendered from any unseen viewpoint.

Metric Based Few-Shot Graph Classification

1 code implementation8 Jun 2022 Donato Crisostomi, Simone Antonelli, Valentino Maiorca, Luca Moschella, Riccardo Marin, Emanuele Rodolà

In this work, we tackle the problem of few-shot graph classification, showing that equipping a simple distance metric learning baseline with a state-of-the-art graph embedder allows to obtain competitive results on the task. While the simplicity of the architecture is enough to outperform more complex ones, it also allows straightforward additions.

Data Augmentation Few-Shot Learning +3

Spectral Maps for Learning on Subgraphs

no code implementations30 May 2022 Marco Pegoraro, Riccardo Marin, Arianna Rampini, Simone Melzi, Luca Cosmo, Emanuele Rodolà

We demonstrate the benefits of incorporating spectral maps in graph learning pipelines, addressing scenarios where a node-to-node map is not well defined, or in the absence of exact isomorphism.

Graph Learning Knowledge Distillation

3D Human Pose Estimation Using Möbius Graph Convolutional Networks

no code implementations20 Mar 2022 Niloofar Azizi, Horst Possegger, Emanuele Rodolà, Horst Bischof

In particular, this allows us to directly and explicitly encode the transformation between joints, resulting in a significantly more compact representation.

3D Human Pose Estimation

Explanatory Learning: Beyond Empiricism in Neural Networks

1 code implementation25 Jan 2022 Antonio Norelli, Giorgio Mariani, Luca Moschella, Andrea Santilli, Giambattista Parascandolo, Simone Melzi, Emanuele Rodolà

We introduce Explanatory Learning (EL), a framework to let machines use existing knowledge buried in symbolic sequences -- e. g. explanations written in hieroglyphic -- by autonomously learning to interpret them.

Binary Classification Program Synthesis

Fish sounds: towards the evaluation of marine acoustic biodiversity through data-driven audio source separation

no code implementations13 Jan 2022 Michele Mancusi, Nicola Zonca, Emanuele Rodolà, Silvia Zuffi

Moreover, one of the causes of biodiversity loss is sound pollution; in data obtained from regions with loud anthropic noise, it is hard to separate the artificial from the fish sound manually.

Audio Source Separation

Smoothness and effective regularizations in learned embeddings for shape matching

1 code implementation14 Dec 2021 Riccardo Marin, Souhaib Attaiki, Simone Melzi, Emanuele Rodolà, Maks Ovsjanikov

In this study, we analyze, for the first time, properties that arise in data-driven learned embedding and their relation to the shape-matching task.


Graph Kernel Neural Networks

no code implementations14 Dec 2021 Luca Cosmo, Giorgia Minello, Michael Bronstein, Emanuele Rodolà, Luca Rossi, Andrea Torsello

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 filter.

Graph Classification

Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach

1 code implementation4 Aug 2021 Marco Pegoraro, Simone Melzi, Umberto Castellani, Riccardo Marin, Emanuele Rodolà

In this work, we address this problem by defining a data-driven model upon a family of linear operators (variants of the mesh Laplacian), whose spectra capture global and local geometric properties of the shape at hand.


Shape registration in the time of transformers

1 code implementation NeurIPS 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.

Cluster-driven Graph Federated Learning over Multiple Domains

no code implementations29 Apr 2021 Debora Caldarola, Massimiliano Mancini, Fabio Galasso, Marco Ciccone, Emanuele Rodolà, Barbara Caputo

Clustering may reduce heterogeneity by identifying the domains, but it deprives each cluster model of the data and supervision of others.

Clustering Federated Learning

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.

Learning Spectral Unions of Partial Deformable 3D Shapes

1 code implementation31 Mar 2021 Luca Moschella, Simone Melzi, Luca Cosmo, Filippo Maggioli, Or Litany, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà

Spectral geometric methods have brought revolutionary changes to the field of geometry processing.

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.


Non-Rigid Puzzles

no code implementations26 Nov 2020 Or Litany, Emanuele Rodolà, Alex Bronstein, Michael Bronstein, Daniel Cremers

We assume to be given a reference shape and its multiple parts undergoing a non-rigid deformation.

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.

Vocal Bursts Intensity Prediction

LIMP: Learning Latent Shape Representations with Metric Preservation Priors

1 code implementation ECCV 2020 Luca Cosmo, Antonio Norelli, Oshri Halimi, Ron Kimmel, Emanuele Rodolà

In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D shapes.

Style Transfer

The Whole Is Greater Than the Sum of Its Nonrigid Parts

1 code implementation27 Jan 2020 Oshri Halimi, Ido Imanuel, Or Litany, Giovanni Trappolini, Emanuele Rodolà, Leonidas Guibas, Ron Kimmel

Here, we claim that observing part of an object which was previously acquired as a whole, one could deal with both partial matching and shape completion in a holistic manner.


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.


Self-supervised Learning of Dense Shape Correspondence

1 code implementation6 Dec 2018 Oshri Halimi, Or Litany, Emanuele Rodolà, Alex Bronstein, Ron Kimmel

The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase.

Self-Supervised Learning

Isospectralization, or how to hear shape, style, and correspondence

1 code implementation CVPR 2019 Luca Cosmo, Mikhail Panine, Arianna Rampini, Maks Ovsjanikov, Michael M. Bronstein, Emanuele Rodolà

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 spectral geometry with a broad range of implications and applications.

Style Transfer

Efficient Deformable Shape Correspondence via Kernel Matching

1 code implementation25 Jul 2017 Zorah Lähner, Matthias Vestner, Amit Boyarski, Or Litany, Ron Slossberg, Tal Remez, Emanuele Rodolà, Alex Bronstein, Michael Bronstein, Ron Kimmel, Daniel Cremers

We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality.

Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space

no code implementations CVPR 2017 Matthias Vestner, Roee Litman, Emanuele Rodolà, Alex Bronstein, Daniel Cremers

Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space.

Density Estimation

Geometric deep learning on graphs and manifolds using mixture model CNNs

4 code implementations CVPR 2017 Federico Monti, Davide Boscaini, Jonathan Masci, Emanuele Rodolà, Jan Svoboda, Michael M. Bronstein

Recently, there has been an increasing interest in geometric deep learning, attempting to generalize deep learning methods to non-Euclidean structured data such as graphs and manifolds, with a variety of applications from the domains of network analysis, computational social science, or computer graphics.

Document Classification Graph Classification +7

Bayesian Inference of Bijective Non-Rigid Shape Correspondence

no code implementations12 Jul 2016 Matthias Vestner, Roee Litman, Alex Bronstein, Emanuele Rodolà, Daniel Cremers

Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space.

Bayesian Inference

Learning shape correspondence with anisotropic convolutional neural networks

no code implementations NeurIPS 2016 Davide Boscaini, Jonathan Masci, Emanuele Rodolà, Michael M. Bronstein

Establishing correspondence between shapes is a fundamental problem in geometry processing, arising in a wide variety of applications.

Efficient Globally Optimal 2D-to-3D Deformable Shape Matching

no code implementations CVPR 2016 Zorah Lähner, Emanuele Rodolà, Frank R. Schmidt, Michael M. Bronstein, Daniel Cremers

We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D shape represented as a planar curve and a 3D shape represented as a surface; the output is a continuous curve on the surface.

3D Shape Retrieval Retrieval

Point-wise Map Recovery and Refinement from Functional Correspondence

no code implementations18 Jun 2015 Emanuele Rodolà, Michael Moeller, Daniel Cremers

Since their introduction in the shape analysis community, functional maps have met with considerable success due to their ability to compactly represent dense correspondences between deformable shapes, with applications ranging from shape matching and image segmentation, to exploration of large shape collections.

Image Segmentation Semantic Segmentation

Partial Functional Correspondence

1 code implementation17 Jun 2015 Emanuele Rodolà, Luca Cosmo, Michael M. Bronstein, Andrea Torsello, Daniel Cremers

In this paper, we propose a method for computing partial functional correspondence between non-rigid shapes.

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