AIConfPaper
← Search

Luca Cosmo

16 accepted papers

2025

COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations

Ruben Ciranni, Giorgio Mariani, Michele Mancusi, Emilian Postolache, Giorgio Fabbro, Emanuele Rodolà +1
ICASSP 2025accepted

We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of the individual stems composing music tracks and can input feat…

Cited by 0Source ↗Scholar ↗
2025

Generating Graphs via Spectral Diffusion

Giorgia Minello, Alessandro Bicciato, Luca Rossi, Andrea Torsello, Luca Cosmo
ICLR 2025poster

In this paper, we present GGSD, a novel graph generative model based on 1) the spectral decomposition of the graph Laplacian matrix and 2) a diffusion process. Specifically, we propose to use a denoising model to sample eigenvectors and eigenvalues from which we can reconstruct the graph Laplacian a…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Naturalistic Music Decoding from EEG Data via Latent Diffusion Models

Emilian Postolache, Natalia Polouliakh, Hiroaki Kitano, Akima Connelly, Emanuele Rodolà, Luca Cosmo +1
ICASSP 2025accepted

In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of reconstructing naturalistic music from electroencephalogram (EEG) recordings. Unlike simpler music with limited timbres, such as MIDI-generated tunes or monophonic piec…

Cited by 0Source ↗Scholar ↗
2024

Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models

Emilian Postolache, Giorgio Mariani, Luca Cosmo, Emmanouil Benetos, Emanuele Rodolà
ICASSP 2024accepted

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the joint distribution over the sources, necessitating pre-separa…

Cited by 0Source ↗Scholar ↗
2024

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

Giorgio Mariani, Irene Tallini, Emilian Postolache, Michele Mancusi, Luca Cosmo, Emanuele Rodolà
ICLR 2024oral

In this work, we define a diffusion-based generative model capable of both music generation and source separation by learning the score of the joint probability density of sources sharing a context. Alongside the classic total inference tasks (i.e., generating a mixture, separating the sources), we…

Cited by 46Source ↗PDF ↗code ↗Scholar ↗
2024

SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes

Mohammad Zohaib*, Luca Cosmo, Alessio Del Bue
ECCV 2024poster

"Unsupervised 3D keypoints estimation from Point Cloud Data (PCD) is a complex task, even more challenging when an object shape is deforming. As keypoints should be semantically and geometrically consistent across all the 3D frames – each keypoint should be anchored to a specific part of the deformi…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Latent Autoregressive Source Separation

Emilian Postolache, Giorgio Mariani, Michele Mancusi, Andrea Santilli, Luca Cosmo, Emanuele Rodolà
AAAI 2023technical

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent spaces (e.g., obtained via VQ-VAE autoencoders), which allow…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

Bending Graphs: Hierarchical Shape Matching Using Gated Optimal Transport

Mahdi Saleh, Shun-Cheng Wu, Luca Cosmo, Nassir Navab, Benjamin Busam, Federico Tombari
CVPR 2022poster

Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain degree of deformation. Existing methods either consider the local description of sampled points or discover corresponde…

Cited by 24PDF ↗code ↗Scholar ↗
2021

Learning disentangled representations via product manifold projection

Marco Fumero, Luca Cosmo, Simone Melzi, Emanuele Rodola
ICML 2021spotlight

We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations. Our method builds upon the idea that the (unknown) low-dimensional manifold underlying the data space can be explicitly modeled as a product of submanifolds. This definition of dise…

Cited by 31Source ↗PDF ↗Scholar ↗
2021

Shape Registration in the Time of Transformers

Giovanni Trappolini, Luca Cosmo, Luca Moschella, Riccardo Marin, Simone Melzi, Emanuele Rodolà
NeurIPS 2021poster

In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. The proposed approach is data-driven and adopts for the first time the transformers architecture in the registration task. Our method is general and applies to different settings. Gi…

Cited by 72Source ↗PDF ↗code ↗Scholar ↗
2021

Universal Spectral Adversarial Attacks for Deformable Shapes

Arianna Rampini, Franco Pestarini, Luca Cosmo, Simone Melzi, Emanuele Rodola
CVPR 2021poster

Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong predictions despite being imperceptible. However, the existence of "universal" attacks (i.e., unique perturbations that transfer across different data points) has only been…

Cited by 19PDF ↗Scholar ↗
2020

LIMP: Learning Latent Shape Representations with Metric Preservation Priors

Luca Cosmo, Antonio Norelli, Oshri Halimi, Ron Kimmel, Emanuele Rodolà
ECCV 2020poster

In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D shapes. Key to our construction is the introduction of a geometric distortion criterion, defined directly on the decoded shapes, translating the preservation of the…

Cited by 87Source ↗PDF ↗Scholar ↗
2020

The Average Mixing Kernel Signature

Luca Cosmo, Giorgia Minello, Michael Bronstein, Luca Rossi, Andrea Torsello
ECCV 2020poster

We introduce the Average Mixing Kernel Signature (AMKS), a novel signature for points on non-rigid three-dimensional shapes based on the average mixing kernel and continuous-time quantum walks. The average mixing kernel holds information on the average transition probabilities of a quantum walk betw…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2019

Isospectralization, or How to Hear Shape, Style, and Correspondence

Luca Cosmo, Mikhail Panine, Arianna Rampini, Maks Ovsjanikov, Michael M. Bronstein, Emanuele Rodola
CVPR 2019poster

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. While theoretically the answer to this question is negative (there exist ex…

Cited by 65PDF ↗Scholar ↗
2017

Parameter-Free Lens Distortion Calibration of Central Cameras

Filippo Bergamasco, Luca Cosmo, Andrea Gasparetto, Andrea Albarelli, Andrea Torsello
ICCV 2017poster

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 with radial distortion is probably the most commonly used, as it balances low complexity with a precision that is sufficient for most applica…

Cited by 20PDF ↗Scholar ↗
2015

Adopting an Unconstrained Ray Model in Light-Field Cameras for 3D Shape Reconstruction

Filippo Bergamasco, Andrea Albarelli, Luca Cosmo, Andrea Torsello, Emanuele Rodola, Daniel Cremers
CVPR 2015poster

Due to their recent availability as off-the-shelf commercial devices, light-field cameras has gathered increasing attention from both scientific community and industrial operators. However, their composite imaging formation process hinders the ability to exploit the well consolidated stack of calibr…

Cited by 22Source ↗PDF ↗Scholar ↗