Home
News
Publications
People
Projects
Contact
Publications
Type
Uncategorized
Conference paper
Journal article
Preprint
Book section
Date
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
ATM: Improving Model Merging by Alternating Tuning and Merging
Preprint
Model merging has recently emerged as a cost-efficient paradigm for multi-task learning. Among current approaches, task arithmetic …
Luca Zhou
,
Daniele Solombrino
,
Donato Crisostomi
,
Maria Sofia Bucarelli
,
Fabrizio Silvestri
,
Emanuele Rodolà
Cite
arXiv
GitHub
ResiDual Transformer Alignment with Spectral Decomposition
Preprint
When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions …
Lorenzo Basile
,
Valentino Maiorca
,
Luca Bortolussi
,
Emanuele Rodolà
,
Francesco Locatello
Cite
arXiv
Detecting and Approximating Redundant Computational Blocks in Neural Networks
Preprint
Deep neural networks often learn similar internal representations, both across different models and within their own layers. While …
Irene Cannistraci
,
Emanuele Rodolà
,
Bastian Rieck
Cite
arXiv
Latent Functional Maps
NeurIPS 2024
Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these …
Marco Fumero
,
Marco Pegoraro
,
Valentino Maiorca
,
Francesco Locatello
,
Emanuele Rodolà
Cite
arXiv
C2M3: Cycle-Consistent Multi-Model Merging
NeurIPS 2024
In this paper, we present a novel data-free method for merging neural networks in weight space. Differently from most existing works, …
Donato Crisostomi
,
Marco Fumero
,
Daniele Baieri
,
Florian Bernard
,
Emanuele Rodolà
Cite
arXiv
GitHub
Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
Preprint
Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various …
Michele Miranda
,
Elena Sofia Ruzzetti
,
Andrea Santilli
,
Fabio Massimo Zanzotto
,
Sebastien Bratieres
,
Emanuele Rodolà
Cite
arXiv
Geometric Epitope and Paratope Prediction
Bioinformatics
Identifying the binding sites of antibodies is essential for developing vaccines and synthetic antibodies. In this article, we …
Marco Pegoraro
,
Clementine Domine
,
Emanuele Rodolà
,
Petar Velickovic
,
Andreea Deac
Cite
URL
PDF
GitHub
ReMatching: Low-Resolution Representations for Scalable Shape Correspondence
ECCV 2024
We introduce ReMatching, a novel shape correspondence solution based on the functional maps framework. Our method, by exploiting a new …
Filippo Maggioli
,
Daniele Baieri
,
Emanuele Rodolà
,
Simone Melzi
Cite
arXiv
GitHub
Naturalistic Music Decoding from EEG Data via Latent Diffusion Models
Preprint
In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of …
Emilian Postolache
,
Natalia Polouliakh
,
Hiroaki Kitano
,
Akima Connelly
,
Emanuele Rodolà
,
Luca Cosmo
,
Taketo Akama
Cite
arXiv
Latent Space Translation via Inverse Relative Projection
Preprint
The emergence of similar representations between independently trained neural models has sparked significant interest in the …
Valentino Maiorca
,
Luca Moschella
,
Marco Fumero
,
Francesco Locatello
,
Emanuele Rodolà
Cite
arXiv
Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
ICLR 2024
In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score …
Giorgio Mariani
,
Irene Tallini
,
Emilian Postolache
,
Michele Mancusi
,
Luca Cosmo
,
Emanuele Rodolà
Cite
PDF
URL
arXiv
GitHub
ICLR 2024 notable top 1.2% (oral)
From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
ICLR 2024
It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are …
Irene Cannistraci
,
Luca Moschella
,
Marco Fumero
,
Valentino Maiorca
,
Emanuele Rodolà
Cite
PDF
URL
ICLR 2024 spotlight
Graph Kernel Neural Networks
TNNLS
The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an …
Luca Cosmo
,
Giorgia Minello
,
Alessandro Bicciato
,
Michael Bronstein
,
Emanuele Rodolà
,
Luca Rossi
,
Andrea Torsello
Cite
URL
arXiv
Implicit-ARAP: Efficient Handle-Guided Deformation of High-Resolution Meshes and Neural Fields via Local Patch Meshing
Preprint
In this work, we present the local patch mesh representation for neural signed distance fields. This technique allows to discretize …
Daniele Baieri
,
Filippo Maggioli
,
Zorah Laehner
,
Simone Melzi
,
Emanuele Rodolà
Cite
arXiv
GitHub
GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splatting
Preprint
We present GSEdit, a pipeline for text-guided 3D object editing based on Gaussian Splatting models. Our method enables the editing of …
Francesco Palandra
,
Andrea Sanchietti
,
Daniele Baieri
,
Emanuele Rodolà
Cite
arXiv
COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
Preprint
We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations …
Ruben Ciranni
,
Emilian Postolache
,
Giorgio Mariani
,
Michele Mancusi
,
Luca Cosmo
,
Emanuele Rodolà
Cite
arXiv
GitHub
SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis
ICASSP 2024
Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and …
Marco Comunità
,
Riccardo F. Gramaccioni
,
Emilian Postolache
,
Emanuele Rodolà
,
Danilo Comminiello
,
Joshua D. Reiss
Cite
PDF
URL
arXiv
GitHub
Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models
ICASSP 2024
Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating …
Emilian Postolache
,
Giorgio Mariani
,
Emmanouil Benetos
,
Luca Cosmo
,
Emanuele Rodolà
Cite
URL
arXiv
Latent spectral regularization for continual learning
PRL
While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget …
Emanuele Frascaroli
,
Riccardo Benaglia
,
Matteo Boschini
,
Luca Moschella
,
Cosimo Fiorini
,
Emanuele Rodolà
,
Simone Calderara
Cite
URL
arXiv
GitHub
Vector Quantile Regression on Manifolds
AISTATS 2024
Quantile regression (QR) is a statistical tool for distribution-free estimation of conditional quantiles of a target variable given …
Marco Pegoraro
,
Sanketh Vedula
,
Aviv A. Rosenberg
,
Irene Tallini
,
Emanuele Rodolà
,
Alex M. Bronstein
Cite
arXiv
GitHub
Camoscio: an Italian Instruction-tuned LLaMA
CLiC-it 2023
In recent years Large Language Models (LLMs) have increased the state of the art on several natural language processing tasks. However, …
Andrea Santilli
,
Emanuele Rodolà
Cite
PDF
GitHub
Best Student Paper Award
A Physically-inspired Approach to the Simulation of Plant Wilting
TOG (Proc. SIGGRAPH Asia 2023)
Plants are among the most complex objects to be modeled in computer graphics. While a large body of work is concerned with structural …
Filippo Maggioli
,
Jonathan Klein
,
Torsten Hadrich
,
Emanuele Rodolà
,
Wojtek Palubicki
,
Soren Pirk
,
Dominik Michels
Cite
URL
PDF
Zero-Shot Duet Singing Voices Separation with Diffusion Models
SDX 2023
In recent studies, diffusion models have shown promise as priors for solving audio inverse problems, including source separation. These …
Chin-Yun Yu
,
Emilian Postolache
,
Emanuele Rodolà
,
Gyorgy Fazekas
Cite
PDF
arXiv
GitHub
Leveraging sparse and shared feature activations for disentangled representation learning
NeurIPS 2023
Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on …
Marco Fumero
,
Florian Wenzel
,
Luca Zancato
,
Alessandro Achille
,
Emanuele Rodolà
,
Stefano Soatto
,
Bernhard Scholkopf
,
Francesco Locatello
Cite
URL
PDF
NeurIPS 2023 spotlight
Latent Space Translation via Semantic Alignment
NeurIPS 2023
Different neural models often exhibit similar latent spaces when exposed to semantically similar data; however, this inherent …
Valentino Maiorca
,
Luca Moschella
,
Antonio Norelli
,
Marco Fumero
,
Francesco Locatello
,
Emanuele Rodolà
Cite
PDF
URL
GitHub
ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training
NeurIPS 2023
CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to …
Antonio Norelli
,
Marco Fumero
,
Valentino Maiorca
,
Luca Moschella
,
Emanuele Rodolà
,
Francesco Locatello
Cite
PDF
html
arXiv
Poster
Thread
GitHub
NeurIPS 2023
Spectral Maps for Learning on Subgraphs
NeurReps 2023
In graph learning, maps between graphs and their subgraphs frequently arise. For instance, when coarsening or rewiring operations are …
Marco Pegoraro
,
Riccardo Marin
,
Arianna Rampini
,
Simone Melzi
,
Luca Cosmo
,
Emanuele Rodolà
Cite
PDF
URL
PDF
Best Paper Award
Geometric Epitope and Paratope Prediction
NeurReps 2023
Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules. In this paper, we …
Marco Pegoraro
,
Clementine Domine
,
Emanuele Rodolà
,
Petar Velickovic
,
Andreea Deac
Cite
bioRxiv
From Charts to Atlas: Merging Latent Spaces into One
NeurReps 2023
Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We …
Donato Crisostomi
,
Irene Cannistraci
,
Luca Moschella
,
Pietro Barbiero
,
Marco Ciccone
,
Pietro Lio
,
Emanuele Rodolà
Cite
URL
PDF
Sparse Vicious Attacks on Graph Neural Networks
IEEE TAI
In this study, we introduce SAVAGE, a novel framework for sparse vicious adversarial link prediction attacks in graph neural networks …
Giovanni Trappolini
,
Valentino Maiorca
,
Silvio Severino
,
Emanuele Rodolà
,
Fabrizio Silvestri
,
Gabriele Tolomei
Cite
URL
GitHub
Fish sounds: towards the evaluation of marine acoustic biodiversity through data-driven audio source separation
I3DA 2023
The marine ecosystem is changing at an alarming rate, exhibiting biodiversity loss and the migration of tropical species to temperate …
Michele Mancusi
,
Nicola Zonca
,
Emanuele Rodolà
,
Silvia Zuffi
Cite
URL
PDF
Zero-shot stitching in Reinforcement Learning using Relative Representations
EWRL 2023
Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. However, …
Antonio Pio Ricciardi
,
Valentino Maiorca
,
Luca Moschella
,
Riccardo Marin
,
Emanuele Rodolà
Cite
URL
PDF
Exploiting Music Source Separation For Singing Voice Detection
MLSP
Singing voice detection (SVD) is an essential task in many music information retrieval (MIR) applications. Deep learning methods have …
Francesco Bonzi
,
Michele Mancusi
,
Simone Del Deo
,
Pierfrancesco Melucci
,
Maria Stella Tavella
,
Loreto Parisi
,
Emanuele Rodolà
Cite
PDF
URL
Continuous Vector Quantile Regression
ICML 2023 Workshop Frontiers4LCD
Vector quantile regression (VQR) estimates the conditional vector quantile function (CVQF), a fundamental quantity which fully …
Sanketh Vedula
,
Irene Tallini
,
Aviv A. Rosenberg
,
Marco Pegoraro
,
Emanuele Rodolà
,
Yaniv Romano
,
Alexander Bronstein
Cite
PDF
URL
Mitigating the Burden of Redundant Datasets via Batch-Wise Unique Samples and Frequency-Aware Losses
ACL 2023
Datasets used to train deep learning models in industrial settings often exhibit skewed distributions with some samples repeated a …
Donato Crisostomi
,
Andrea Caciolai
,
Alessandro Pedrani
,
Kay Rottmann
,
Alessandro Manzotti
,
Enrico Palumbo
,
Davide Bernardi
Cite
URL
AVEN-GR: Attribute Value Extraction and Normalization using product GRaphs
ACL 2023
Getting a good understanding of the user intent is vital for e-commerce applications to surface the right product to a given customer …
Donato Crisostomi
,
Thomas Ricatte
Cite
URL
Fauno - The Italian Large Language Model that will leave you senza parole!
IIR 2023
This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM). Our goal with Fauno is …
Andrea Bacciu
,
Giovanni Trappolini
,
Andrea Santilli
,
Emanuele Rodolà
,
Fabrizio Silvestri
Cite
PDF
GitHub
Adversarial Permutation Invariant Training for Universal Sound Separation
ICASSP 2023
Universal sound separation consists of separating mixes with arbitrary sounds of different types, and permutation invariant training …
Emilian Postolache
,
Jordi Pons
,
Santiago Pascual
,
Joan Serrà
Cite
URL
arXiv
Accelerating Transformer Inference for Translation via Parallel Decoding
ACL 2023
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network …
Andrea Santilli
,
Silvio Severino
,
Emilian Postolache
,
Valentino Maiorca
,
Michele Mancusi
,
Riccardo Marin
,
Emanuele Rodolà
Cite
PDF
arXiv
GitHub
Multimodal Neural Databases
SIGIR 2023
The rise in loosely-structured data available through text, images, and other modalities has called for new ways of querying them. …
Giovanni Trappolini
,
Andrea Santilli
,
Emanuele Rodolà
,
Alon Halevy
,
Fabrizio Silvestri
Cite
PDF
arXiv
Attention-likelihood relationship in transformers
Tiny ICLR 2023
We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to …
Valeria Ruscio
,
Valentino Maiorca
,
Fabrizio Silvestri
Cite
URL
PDF
GitHub
Bootstrapping Parallel Anchors for Relative Representations
Tiny ICLR 2023
The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot …
Irene Cannistraci
,
Luca Moschella
,
Valentino Maiorca
,
Marco Fumero
,
Antonio Norelli
,
Emanuele Rodolà
Cite
PDF
URL
Relative representations enable zero-shot latent space communication
ICLR 2023
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. …
Luca Moschella
,
Valentino Maiorca
,
Marco Fumero
,
Antonio Norelli
,
Francesco Locatello
,
Emanuele Rodolà
Cite
PDF
URL
GitHub
Slides
ICLR 2023 notable top 5%
Latent Autoregressive Source Separation
AAAI 2023
Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task …
Emilian Postolache
,
Giorgio Mariani
,
Michele Mancusi
,
Andrea Santilli
,
Luca Cosmo
,
Emanuele Rodolà
Cite
arXiv
GitHub
Play música alegre: A Large-Scale Empirical Analysis of Cross-Lingual Phenomena in Voice Assistant Interactions
MMNLU workshop, EMNLP 2022
Cross-lingual phenomena are quite common in informal contexts like social media, where users are likely to mix their native language …
Donato Crisostomi
,
Alessandro Manzotti
,
Enrico Palumbo
,
Davide Bernardi
,
Sarah Campbell
,
Shubham Garg
Cite
URL
Metric Based Few-Shot Graph Classification
LoG 2022
Few-shot graph classification is a novel yet promising emerging research field that still lacks the soundness of well-established …
Donato Crisostomi
,
Simone Antonelli
,
Valentino Maiorca
,
Luca Moschella
,
Riccardo Marin
,
Emanuele Rodolà
Cite
URL
PDF
GitHub
Bloom: A 176b-parameter open-access multilingual language model
Preprint
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language …
BIG-Science contributors including
,
Andrea Santilli
Cite
PDF
arXiv
Certification of Gaussian Boson Sampling via graphs feature vectors and kernels
QST
Gaussian Boson Sampling (GBS) is a non-universal model for quantum computing inspired by the original formulation of the Boson Sampling …
Taira Giordani
,
Valerio Mannucci
,
Nicolò Spagnolo
,
Marco Fumero
,
Arianna Rampini
,
Emanuele Rodolà
,
Fabio Sciarrino
Cite
URL
PDF
3D Human Pose Estimation Using Möbius Graph Convolutional Networks
ECCV 2022
3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph …
Niloofar Azizi
,
Horst Possegger
,
Emanuele Rodolà
,
Horst Bischof
Cite
URL
PDF
Few-Shot Object Detection: A Survey
ACM Surveys
Deep learning approaches have recently raised the bar in many fields, from Natural Language Processing to Computer Vision, by …
Simone Antonelli
,
Danilo Avola
,
Luigi Cinque
,
Donato Crisostomi
,
Gian Luca Foresti
,
Fabio Galasso
,
Marco Raoul Marini
,
Alessio Mecca
,
Daniele Pannone
Cite
URL
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
ACL 2022
PromptSource is a system for creating, sharing, and using natural language prompts. Prompts are functions that map an example from a …
Stephen Bach
,
Victor Sanh
,
Zheng Xin Yong
,
Albert Webson
,
Colin Raffel
,
BIG-Science contributors including
,
Andrea Santilli
Cite
PDF
ACL 2022 Demo
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their …
442 authors including
,
Andrea Santilli
,
Antonio Norelli
,
Emanuele Rodolà
,
Giambattista Parascandolo
,
Giorgio Mariani
,
Luca Moschella
,
Simone Melzi
Cite
PDF
arXiv
Smoothness and effective regularizations in learned embeddings for shape matching
Preprint
Many innovative applications require establishing correspondences among 3D geometric objects. However, the countless possible …
Riccardo Marin
,
Souhaib Attaiki
,
Simone Melzi
,
Emanuele Rodolà
,
Maks Ovsjanikov
Cite
URL
PDF
CLIP-Forge: Towards Zero-Shot Text-To-Shape Generation
CVPR 2022
Generating shapes using natural language can enable new ways of imagining and creating the things around us. While significant recent …
Aditya Sanghi
,
Hang Chu
,
Joseph G. Lambourne
,
Ye Wang
,
Chin-Yi Cheng
,
Marco Fumero
,
Kamal Rahimi Malekshan
Cite
Multimodal Feature Fusion and Knowledge-Driven Learning via Experts Consult for Thyroid Nodule Classification
TCSVT
Computer-aided diagnosis (CAD) is becoming a prominent approach to assist clinicians spanning across multiple fields. These automated …
Danilo Avola
,
Luigi Cinque
,
Alessio Fagioli
,
Sebastiano Filetti
,
Giorgio Grani
,
Emanuele Rodolà
Cite
URL
PDF
Learning Spectral Unions of Partial Deformable 3D Shapes
CGF (Proc. EG 2022)
Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study …
Luca Moschella
,
Simone Melzi
,
Luca Cosmo
,
Filippo Maggioli
,
Or Litany
,
Maks Ovsjanikov
,
Leonidas Guibas
,
Emanuele Rodolà
Cite
PDF
URL
Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching
NeurIPS 2022
In this work we present a novel approach for computing correspondences between non-rigid objects, by exploiting a reduced …
Riccardo Marin
,
Emanuele Rodolà
,
Maks Ovsjanikov
,
Ramana Subramanyam Sundararaman
Cite
PDF
URL
GitHub
PC-GAU: PCA Basis of Scattered Gaussians for Shape Matching via Functional Maps
STAG 2022
Shape matching is a central problem in geometry processing applications, ranging from texture transfer to statistical shape analysis. …
Michele Colombo
,
Giacomo Boracchi
,
Simone Melzi
Cite
PDF
GitHub
Olivaw: Mastering othello without human knowledge, nor a penny
IEEE ToG
AlphaGo Zero for Othello. With two ideas to speed up the learning, and tested in a live match against a former world champion.
Antonio Norelli
,
Alessandro Panconesi
Cite
PDF
arXiv
Newton's Fractals on Surfaces via Bicomplex Algebra
SIGGRAPH 2022 Posters
An algorithm that exploits features of the bicomplex field to compute 4-dimensional Newton fractals for procedural texturing applications. The generated fractals are computed in a pixel shader only on the target surface to achieve real-time performance.
Filippo Maggioli
,
Daniele Baieri
,
Simone Melzi
,
Emanuele Rodolà
Cite
PDF
GitHub
Neural Implicit Style-net: synthesizing shapes in a preferred style exploiting self supervision
NeurReps 2022
We introduce a novel approach to disentangle style from content in the 3D domain and perform unsupervised neural style transfer. Our …
Marco Fumero
,
Hooman Shayani
,
Aditya Sanghi
,
Emanuele Rodolà
Cite
URL
PDF
MoMaS: Mold Manifold Simulation for real-time procedural texturing
CGF (Proc. PG 2022)
A generalization of the algorithm for simulating the evolution of slime mold organisms to work on triangular meshes. The algorithm is implemented on GPU to achieve real-time performance.
Filippo Maggioli
,
Riccardo Marin
,
Simone Melzi
,
Emanuele Rodolà
Cite
PDF
Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach
CGF (Proc. SGP 2022)
Many natural shapes have most of their characterizing features concentrated over a few regions in space. For example, humans and …
Marco Pegoraro
,
Simone Melzi
,
Umberto Castellani
,
Riccardo Marin
,
Emanuele Rodolà
Cite
PDF
URL
GitHub
KiloNeuS: A Versatile Neural Implicit Surface Representation for Real-Time Rendering
Preprint
A neural implicit representation which couples solving for a well-defined surface and real-time rendering capabilities.
Stefano Esposito
,
Daniele Baieri
,
Stefan Zellmann
,
André Hinkenjann
,
Emanuele Rodolà
Cite
arXiv
GIM3D: A 3D Dataset for Garment Segmentation
STAG 2022
The 3D cloth segmentation task is particularly challenging due to the extreme variation of shapes, even among the same category of …
Pietro Musoni
,
Simone Melzi
,
Umberto Castellani
Cite
PDF
GitHub
Explanatory learning: Beyond empiricism in neural networks
Preprint
When a ML system becomes an artificial scientist: mastering the game of Zendo with Transformers.
Antonio Norelli
,
Giorgio Mariani
,
Luca Moschella
,
Andrea Santilli
,
Giambattista Parascandolo
,
Simone Melzi
,
Emanuele Rodolà
Cite
PDF
GitHub
arXiv
Thread
Errare humanum est? a pilot study to evaluate the human-likeness of a AI othello playing agent
IVA 2022
Olivaw is an AI Othello playing agent which autonomously learns how to improve its gameplay by playing against itself. Some top-notch …
Enrico Lauletta
,
Beatrice Biancardi
,
Antonio Norelli
,
Maurizio Mancini
,
Alessandro Panconesi
Cite
PDF
URL
Complex Functional Maps: A Conformal Link Between Tangent Bundles
CGF
Abstract In this paper, we introduce complex functional maps, which extend the functional map framework to conformal maps between …
Nicolas Donati
,
Etienne Corman
,
Simone Melzi
,
Maks Ovsjanikov
Cite
URL
GitHub
AI-based Data Preparation and Data Analytics in Healthcare: The Case of Diabetes
Preprint
The Associazione Medici Diabetologi (AMD) collects and manages one of the largest worldwide available collections of diabetic patient …
Marianna Maranghi
,
Aris Anagnostopoulos
,
Irene Cannistraci
,
Ioannis Chatzigiannakis
,
Federico Croce
,
Giulia Di Teodoro
,
Michele Gentile
,
Giorgio Grani
,
Maurizio Lenzerini
,
Stefano Leonardi
,
Andrea Mastropietro
,
Laura Palagi
,
Massimiliano Pappa
,
Riccardo Rosati
,
Riccardo Valentini
,
Paola Velardi
Cite
PDF
URL
A Novel GAN-Based Anomaly Detection and Localization Method for Aerial Video Surveillance at Low Altitude
Remote Sensing
The last two decades have seen an incessant growth in the use of Unmanned Aerial Vehicles (UAVs) equipped with HD cameras for …
Danilo Avola
,
Irene Cannistraci
,
Marco Cascio
,
Luigi Cinque
,
Anxhelo Diko
,
Alessio Fagioli
,
Gian Luca Foresti
,
Romeo Lanzino
,
Maurizio Mancini
,
Alessio Mecca
,
Daniele Pannone
Cite
PDF
3D Shape Analysis Through a Quantum Lens: the Average Mixing Kernel Signature
IJCV
The Average Mixing Kernel Signature is a novel spectral signature for points on non-rigid three-dimensional shapes. It is based on a …
Luca Cosmo
,
Giorgia Minello
,
Michael M. Bronstein
,
Emanuele Rodolà
,
Luca Rossi
,
Andrea Torsello
Cite
URL
GitHub
Multitask Prompted Training Enables Zero-Shot Task Generalization
ICLR 2022
Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., …
Victor Sanh
,
Albert Webson
,
Colin Raffel
,
Stephen H. Bach
,
BIG-Science contributors including
,
Andrea Santilli
Cite
PDF
ICLR 2022 (Oral)
Spectral Shape Recovery and Analysis via Data-driven Connections
IJCV
We introduce a novel learning-based method to recover shapes from their Laplacian spectra, based on establishing and exploring …
Riccardo Marin
,
Arianna Rampini
,
Umberto Castellani
,
Emanuele Rodolà
,
Maks Ovsjanikov
,
Simone Melzi
Cite
URL
GitHub
Learning disentangled representations via product manifold projection
ICML 2021
We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations. Our method …
Marco Fumero
,
Luca Cosmo
,
Simone Melzi
,
Emanuele Rodolà
Cite
PDF
URL
Shape registration in the time of transformers
NeurIPS 2021
In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. The proposed …
Giovanni Trappolini
,
Luca Cosmo
,
Luca Moschella
,
Riccardo Marin
,
Simone Melzi
,
Emanuele Rodolà
Cite
PDF
NeurIPS 2021
Universal Spectral Adversarial Attacks for Deformable Shapes
CVPR 2021
Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong …
Arianna Rampini
,
Franco Pestarini
,
Luca Cosmo
,
Simone Melzi
,
Emanuele Rodolà
Cite
URL
PDF
GitHub
Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence With Functional Maps
CVPR 2021
In this paper, we provide a theoretical foundation for pointwise map recovery from functional maps and highlight its relation to a …
Gautam Pai
,
Jing Ren
,
Simone Melzi
,
Peter Wonka
,
Maks Ovsjanikov
Cite
URL
GitHub
Cluster-driven Graph Federated Learning over Multiple Domains
CVPR L2ID 2021
Federated Learning (FL) deals with learning a central model (i.e. the server) in privacy-constrained scenarios, where data are stored …
Debora Caldarola
,
Massimiliano Mancini
,
Fabio Galasso
,
Marco Ciccone
,
Emanuele Rodolà
,
Barbara Caputo
Cite
URL
PDF
Wavelet-based Heat Kernel Derivatives: Towards Informative Localized Shape Analysis
CGF
Abstract In this paper, we propose a new construction for the Mexican hat wavelets on shapes with applications to partial shape …
Maxime Kirgo
,
Simone Melzi
,
Giuseppe Patanè
,
Emanuele Rodolà
,
Maks Ovsjanikov
Cite
PDF
URL
GitHub
Unsupervised source separation via Bayesian inference in the latent domain
Preprint
State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling …
Michele Mancusi
,
Emilian Postolache
,
Giorgio Mariani
,
Marco Fumero
,
Andrea Santilli
,
Luca Cosmo
,
Emanuele Rodolà
Cite
arXiv
GitHub
Reposing and retargeting unrigged characters with intrinsic-extrinsic transfer
STAG 2021
In the 3D digital world, deformations and animations of shapes are fundamental topics for several applications. The entertainment …
Pietro Musoni
,
Riccardo Marin
,
Simone Melzi
,
Umberto Castellani
Cite
URL
Orthogonalized Fourier polynomials for signal approximation and transfer
CGF (Proc. EG 2021)
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.
Filippo Maggioli
,
Simone Melzi
,
Maks Ovsjanikov
,
Michael M. Bronstein
,
Emanuele Rodolà
Cite
PDF
GitHub
Intra-operative Update of Boundary Conditions for Patient-Specific Surgical Simulation
MICCAI 2021
Patient-specific Biomechanical Models (PBMs) can enhance computer assisted surgical procedures with critical information. Although …
Eleonora Tagliabue
,
Marco Piccinelli
,
Diego Dall'Alba
,
Juan Verde
,
Micha Pfeiffer
,
Riccardo Marin
,
Stefanie Speidel
,
Paolo Fiorini
,
Stéphane Cotin
Cite
Efficiently parallelizable strassen-based multiplication of a matrix by its transpose
ICPP 2021
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.
Viviana Arrigoni
,
Filippo Maggioli
,
Annalisa Massini
,
Emanuele Rodolà
Cite
PDF
GitHub
Discrete Optimization for Shape Matching
CGF
Abstract We propose a novel discrete solver for optimizing functional map-based energies, including descriptor preservation and …
Jing Ren
,
Simone Melzi
,
Peter Wonka
,
Maks Ovsjanikov
Cite
URL
PDF
GitHub
Nonlinear Spectral Geometry Processing via the TV Transform
TOG (Proc. SIGGRAPH Asia 2020)
We introduce a novel computational framework for digital geometry processing, based upon the derivation of a nonlinear operator …
Marco Fumero
,
Michael Möller
,
Emanuele Rodolà
Cite
URL
arXiv
MapTree: Recovering Multiple Solutions in the Space of Maps
TOG (Proc. SIGGRAPH Asia 2020)
In this paper we propose an approach for computing multiple high-quality near-isometric dense correspondences between a pair of 3D …
Jing Ren
,
Simone Melzi
,
Maks Ovsjanikov
,
Peter Wonka
Cite
URL
PDF
GitHub
Instant recovery of shape from spectrum via latent space connections
3DV 2020
We introduce the first learning-based method for recovering shapes from Laplacian spectra. Given an auto-encoder, our model takes the …
Riccardo Marin
,
Arianna Rampini
,
Umberto Castellani
,
Emanuele Rodolà
,
Maks Ovsjanikov
,
Simone Melzi
Cite
PDF
GitHub
Best Student Paper Award
2D Skeleton-Based Action Recognition via Two-Branch Stacked LSTM-RNNs
IEEE ToM
Action recognition in video sequences is an interesting field for many computer vision applications, including behavior analysis, event …
Danilo Avola
,
Marco Cascio
,
Luigi Cinque
,
Gianluca Foresti
,
Cristiano Massaroni
,
Emanuele Rodolà
Cite
URL
Towards Precise Completion of Deformable Shapes
ECCV 2020
According to Aristotle, the whole is greater than the sum of its parts. This statement was adopted to explain human perception by the …
Oshri Halimi
,
Ido Imanuel
,
Or Litany
,
Giovanni Trappolini
,
Emanuele Rodolà
,
Leo Guibas
,
Ron Kimmel
Cite
URL
PDF
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations
EMNLP 2020
Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality …
Fabio Massimo Zanzotto
,
Andrea Santilli
,
Leonardo Ranaldi
,
Dario Onorati
,
Pierfrancesco Tommasino
,
Francesca Fallucchi
Cite
URL
FARM: Functional automatic registration method for 3D human bodies
CGF
We introduce a new method for non-rigid registration of 3D human shapes. Our proposed pipeline builds upon a given parametric model of …
Riccardo Marin
,
Simone Melzi
,
Emanuele Rodolà
,
Umberto Castellani
Cite
arXiv
URL
GitHub
The Average Mixing Kernel Signature
ECCV 2020
We introduce the Average Mixing Kernel Signature (AMKS), a novel signature for points on non-rigid three-dimensional shapes based on …
Luca Cosmo
,
Giorgia Minello
,
Michael M. Bronstein
,
Luca Rossi
,
Andrea Torsello
Cite
PDF
GitHub
LIMP: Learning Latent Shape Representations with Metric Preservation Priors
ECCV 2020
In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D …
Luca Cosmo
,
Antonio Norelli
,
Oshri Halimi
,
Ron Kimmel
,
Emanuele Rodolà
Cite
arXiv
GitHub
Intrinsic/extrinsic embedding for functional remeshing of 3D shapes
CAG
3D acquisition pipeline delivers 3D digital models accurately representing real-world objects, improving the geometric accuracy and …
Simone Melzi
,
Riccardo Marin
,
Pietro Musoni
,
Filippo Bardon
,
Marco Tarini
,
Umberto Castellani
Cite
URL
GitHub
Generating Adversarial Surfaces via Band-Limited Perturbations
CGF (Proc. SGP 2020)
Adversarial attacks have demonstrated remarkable efficacy in altering the output of a learning model by applying a minimal perturbation …
Giorgio Mariani
,
Luca Cosmo
,
Alex M. Bronstein
,
Emanuele Rodolà
Cite
URL
GitHub
Experimental device-independent certified randomness generation with an instrumental causal structure
CommsPhys
The intrinsic random nature of quantum physics offers novel tools for the generation of random numbers, a central challenge for a …
Iris Agresti
,
Davide Poderini
,
Leonardo Guerini
,
Michele Mancusi
,
Gonzalo Carvacho
,
Leandro Aolita
,
Daniel Cavalcanti
,
Rafael Chaves
,
Fabio Sciarrino
Cite
Communications Physics
Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning
Nature Methods
Predicting interactions between proteins and other biomolecules solely based on structure remains a challenge in biology. A high-level …
Pablo Gainza
,
Freyr Sverrisson
,
Federico Monti
,
Emanuele Rodolà
,
Davide Boscaini
,
Michael M. Bronstein
,
Bruno Correia
Cite
URL
GitHub
A parametric analysis of discrete Hamiltonian functional maps
CGF (Proc. SGP 2020)
Abstract In this paper we develop an in-depth theoretical investigation of the discrete Hamiltonian eigenbasis, which remains quite …
Emilian Postolache
,
Marco Fumero
,
Luca Cosmo
,
Emanuele Rodolà
Cite
PDF
URL
Learning interaction patterns from surface representations of protein structure
NeurIPS 2019 Workshops
Predicting interactions between proteins and other biomolecules purely based on structure is an unsolved problem in biology. The …
Pablo Gainza
,
Freyr Sverrisson
,
Federico Monti
,
Emanuele Rodolà
,
Michael M. Bronstein
,
Bruno Correia
Cite
URL
PDF
ZoomOut: Spectral Upsampling for Efficient Shape Correspondence
TOG (Proc. SIGGRAPH Asia 2019)
We present a simple and efficient method for refining maps or correspondences by iterative upsampling in the spectral domain that can …
Simone Melzi
,
Jing Ren
,
Emanuele Rodolà
,
Abhishek Sharma
,
Peter Wonka
,
Maks Ovsjanikov
Cite
URL
PDF
GitHub
High-Resolution Augmentation for Automatic Template-Based Matching of Human Models
3DV 2019
We propose a new approach for 3D shape matching of deformable human shapes. Our approach is based on the joint adoption of three …
Riccardo Marin
,
Simone Melzi
,
Emanuele Rodolà
,
Umberto Castellani
Cite
arXiv
URL
GitHub
Correspondence-Free Region Localization for Partial Shape Similarity via Hamiltonian Spectrum Alignment
3DV 2019
We consider the problem of localizing relevant subsets of non-rigid geometric shapes given only a partial 3D query as the input. Such …
Arianna Rampini
,
Irene Tallini
,
Maks Ovsjanikov
,
Alex M. Bronstein
,
Emanuele Rodolà
Cite
URL
PDF
GitHub
Best Paper Award
Unsupervised learning of dense shape correspondence
CVPR 2019
We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the …
Oshri Halimi
,
Or Litany
,
Emanuele Rodolà
,
Alex M. Bronstein
,
Ron Kimmel
Cite
URL
PDF
GitHub
GFrames: Gradient-based local reference frame for 3D shape matching
CVPR 2019
We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the …
Simone Melzi
,
Riccardo Spezialetti
,
Federico Tombari
,
Michael M. Bronstein
,
Luigi Di Stefano
,
Emanuele Rodolà
Cite
URL
PDF
GitHub
SHREC'19: Shape Correspondence with Isometric and Non-Isometric Deformations
3DOR 2019
The registration of non-rigidly deforming shapes is a fundamental problem in the area of Graphics and Computational Geometry. One of …
R.M. Dyke
,
C. Stride
,
Y.-K. Lai
,
P.L. Rosin
,
M. Aubry
,
A. Boyarski
,
A.M. Bronstein
,
M.M. Bronstein
,
Daniel Cremers
,
M. Fisher
,
T. Groueix
,
D. Guo
,
V. Kim
,
R. Kimmel
,
Z. Lähner
,
K. Li
,
O. Litany
,
T. Remez
,
Emanuele Rodolà
,
B.C. Russell
,
Y. Sahillioglu
,
R. Slossberg
,
G. Tam
,
M. Vestner
,
Z. Wu
,
J. Yang
Cite
PDF
URL
SHREC'19: Matching humans with different connectivity
3DOR 2019
Objects Matching is a ubiquitous problem in computer science with particular relevance for many applications; property transfer between …
Simone Melzi
,
Riccardo Marin
,
Emanuele Rodolà
,
U. Castellani
,
J. Ren
,
A. Poulenard
,
P. Wonka
,
M. Ovsjanikov
Cite
URL
GitHub
Functional maps representation on product manifolds
CGF (Proc. SGP 2019)
We consider the tasks of representing, analyzing and manipulating maps between shapes. We model maps as densities over the product …
Emanuele Rodolà
,
Zorah Lähner
,
Alex M. Bronstein
,
Michael M. Bronstein
,
Justin Solomon
Cite
URL
PDF
Isospectralization, or how to hear shape, style, and correspondence
CVPR 2019
The question whether one can recover the shape of a geometric object from its Laplacian spectrum (‘hear the shape of the …
Luca Cosmo
,
Mikhail Panine
,
Arianna Rampini
,
Maks Ovsjanikov
,
Michael M. Bronstein
,
Emanuele Rodolà
Cite
PDF
GitHub
A Kernel-based Approach for Irony and Sarcasm Detection in Italian
EVALITA 2018
This paper describes the UNITOR system that participated to the Irony Detection in Italian Tweets task (IronITA) within the context of …
Andrea Santilli
,
Danilo Croce
,
Roberto Basili
Cite
PDF
URL
GitHub
Best System Award Nomination
Localized manifold harmonics for spectral shape analysis
CGF
The use of Laplacian eigenfunctions is ubiquitous in a wide range of computer graphics and geometry processing applications. In …
Simone Melzi
,
Emanuele Rodolà
,
Umberto Castellani
,
Michael M. Bronstein
Cite
URL
PDF
GitHub
SyntNN at SemEval-2018 Task 2: is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptrons
SemEval 2018
In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of …
Andrea Santilli
,
Fabio Massimo Zanzotto
Cite
URL
Improved functional mappings via product preservation
CGF (Proc. EG 2018)
In this paper, we consider the problem of information transfer across shapes and propose an extension to the widely used functional map …
Dorian Nogneng
,
Simone Melzi
,
Emanuele Rodolà
,
Umberto Castellani
,
Michael M. Bronstein
,
Maks Ovsjanikov
Cite
URL
PDF
GitHub
Regularized Point-wise Map Recovery from Functional Correspondence
CGF
The concept of using functional maps for representing dense correspondences between deformable shapes has proven to be extremely …
Emanuele Rodolà
,
Michael Moeller
,
Daniel Cremers
Cite
URL
PDF
Spatial Maps: From low rank spectral to sparse spatial functional representations
3DV 2017
Functional representation is a well-established approach to represent dense correspondences between deformable shapes. The approach …
Andrea Gasparetto
,
Luca Cosmo
,
Emanuele Rodolà
,
Michael M. Bronstein
,
Andrea Torsello
Cite
PDF
Efficient deformable shape correspondence via kernel matching
3DV 2017
We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality. We formulate …
Matthias Vestner
,
Zorah Lähner
,
Amit Boyarski
,
Or Litany
,
Ron Slossberg
,
Tal Remez
,
Emanuele Rodolà
,
Alex M. Bronstein
,
Michael M. Bronstein
,
Ron Kimmel
,
Daniel Cremers
Cite
URL
PDF
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
ICCV 2017
We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model …
Or Litany
,
Tal Remez
,
Emanuele Rodolà
,
Alex M. Bronstein
,
Michael M. Bronstein
Cite
PDF
URL
GitHub
Effects of Network Topology on the OpenAnswer's Bayesian Model of Peer Assessment
EC-TEL 2017
The paper investigates if and how the topology of the peer-assessment network can affect the performance of the Bayesian model adopted …
Maria De Marsico
,
Luca Moschella
,
Andrea Sterbini
,
Marco Temperini
Cite
PDF
EC-TEL 2017
Performance Variations of the Bayesian Model of Peer-Assessment Implemented in OpenAnswer Response to Modifications of the Number of Peers Assessed and of the Quality of the Class
ITHET 2017
The paper presents a study of the performance variations of the Bayesian model of peer-assessment implemented in OpenAnswer, in terms …
Maria De Marsico
,
Luca Moschella
,
Andrea Sterbini
,
Marco Temperini
Cite
PDF
ITHET 2017
Product Manifold Filter: Non-rigid shape correspondence via kernel density estimation in the product space
CVPR 2017
Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a …
Matthias Vestner
,
Roee Litman
,
Emanuele Rodolà
,
Alex M. Bronstein
,
Daniel Cremers
Cite
URL
PDF
Geometric deep learning on graphs and manifolds using mixture model CNNs
CVPR 2017
Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural …
Federico Monti
,
Davide Boscaini
,
Jonathan Masci
,
Emanuele Rodolà
,
Jan Svoboda
,
Michael M. Bronstein
Cite
URL
PDF
Fully spectral partial shape matching
CGF (Proc. EG 2017)
We propose an efficient procedure for calculating partial dense intrinsic correspondence between deformable shapes performed entirely …
Or Litany
,
Emanuele Rodolà
,
Alex M. Bronstein
,
Michael M. Bronstein
Cite
URL
PDF
GitHub
SHREC'17: Deformable shape retrieval with missing parts
3DOR 2017
Partial similarity problems arise in numerous applications that involve real data acquisition by 3D sensors, inevitably leading to …
Emanuele Rodolà
,
Luca Cosmo
,
O. Litany
,
M. M. Bronstein
,
A. M. Bronstein
,
N. Audebert
,
A. B. Hamza
,
A. Boulch
,
U. Castellani
,
M. N. Do
,
others
Cite
PDF
URL
Partial Functional Correspondence
CGF
In this paper, we propose a method for computing partial functional correspondence between non-rigid shapes. We use perturbation …
Emanuele Rodolà
,
Luca Cosmo
,
Michael M. Bronstein
,
Andrea Torsello
,
Daniel Cremers
Cite
PDF
URL
Consistent Partial Matching of Shape Collections via Sparse Modeling
CGF
Recent efforts in the area of joint object matching approach the problem by taking as input a set of pairwise maps, which are then …
Luca Cosmo
,
Emanuele Rodolà
,
Andrea Albarelli
,
Facundo Mémoli
,
Daniel Cremers
Cite
PDF
URL
Computing and Processing Correspondences with Functional Maps
SIGGRAPH 2017 Courses
Notions of similarity and correspondence between geometric shapes and images are central to many tasks in geometry processing, computer …
Maks Ovsjanikov
,
Etienne Corman
,
Michael M. Bronstein
,
Emanuele Rodolà
,
Mirela Ben-Chen
,
Leo Guibas
,
Frederic Chazal
,
Alex M. Bronstein
Cite
URL
Learning shape correspondence with anisotropic convolutional neural networks
NIPS 2016
Establishing correspondence between shapes is a fundamental problem in geometry processing, arising in a wide variety of applications. …
Davide Boscaini
,
Jonathan Masci
,
Emanuele Rodolà
,
Michael M. Bronstein
Cite
PDF
URL
GitHub
An Accurate and Robust Artificial Marker Based on Cyclic Codes
TPAMI
Artificial markers are successfully adopted to solve several vision tasks, ranging from tracking to calibration. While most designs …
Filippo Bergamasco
,
Andrea Albarelli
,
Luca Cosmo
,
Emanuele Rodolà
,
Andrea Torsello
Cite
URL
A Game-theoretical Approach for Joint Matching of Multiple Feature throughout Unordered Images
ICPR 2016
Feature matching is a key step in most Computer Vision tasks involving several views of the same subject. In fact, it plays a crucial …
Luca Cosmo
,
Andrea Albarelli
,
Filippo Bergamasco
,
Andrea Torsello
,
Emanuele Rodolà
,
Daniel Cremers
Cite
PDF
Shape analysis with anisotropic windowed Fourier transform
3DV 2016
We propose Anisotropic Windowed Fourier Transform (AWFT), a framework for localized space-frequency analysis of deformable 3D shapes. …
Simone Melzi
,
Emanuele Rodolà
,
Umberto Castellani
,
Michael M. Bronstein
Cite
PDF
URL
Coupled functional maps
3DV 2016
Classical formulations of the shape matching problem involve the definition of a matching cost that directly depends on the action of …
Davide Eynard
,
Emanuele Rodolà
,
Klaus Glashoff
,
Michael M. Bronstein
Cite
PDF
URL
Non-rigid puzzles
CGF (Proc. SGP 2016)
Shape correspondence is a fundamental problem in computer graphics and vision, with applications in various problems including …
Or Litany
,
Emanuele Rodolà
,
Alex M. Bronstein
,
Michael M. Bronstein
,
Daniel Cremers
Cite
PDF
URL
GitHub
Best Paper Award
Efficient globally optimal 2d-to-3d deformable shape matching
CVPR 2016
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 …
Zorah Lähner
,
Emanuele Rodolà
,
Frank Schmidt
,
Michael M. Bronstein
,
Daniel Cremers
Cite
PDF
URL
GitHub
Anisotropic Diffusion Descriptors
CGF (Proc. EG 2016)
Spectral methods have recently gained popularity in many domains of computer graphics and geometry processing, especially shape …
Davide Boscaini
,
Jonathan Masci
,
Emanuele Rodolà
,
Michael M. Bronstein
,
Daniel Cremers
Cite
PDF
URL
SHREC'16: Matching of deformable shapes with topological noise
3DOR 2016
A particularly challenging setting of the shape matching problem arises when the shapes being matched have topological artifacts due to …
Z. Lähner
,
Emanuele Rodolà
,
M. M. Bronstein
,
Daniel Cremers
,
O. Burghard
,
Luca Cosmo
,
A. Dieckmann
,
R. Klein
,
Y. Sahillioglu
Cite
PDF
SHREC'16: Partial matching of deformable shapes
3DOR 2016
Matching deformable 3D shapes under partiality transformations is a challenging problem that has received limited focus in the computer …
Luca Cosmo
,
Emanuele Rodolà
,
Michael M. Bronstein
,
Andrea Torsello
,
Daniel Cremers
,
Yusuf Sahillioǧlu
Cite
PDF
URL
Matching deformable objects in clutter
3DV 2016
We consider the problem of deformable object detection and dense correspondence in cluttered 3D scenes. Key ingredient to our method is …
Luca Cosmo
,
Emanuele Rodolà
,
Jonathan Masci
,
Andrea Torsello
,
Michael M. Bronstein
Cite
PDF
Geometric Deep Learning
SIGGA 2016 Courses
The goal of these course notes is to describe the main mathematical ideas behind geometric deep learning and to provide implementation …
Jonathan Masci
,
Emanuele Rodolà
,
Davide Boscaini
,
Michael M. Bronstein
,
Hao Li
Cite
URL
Computing and Processing Correspondences with Functional Maps
SIGGA 2016 Courses
Notions of similarity and correspondence between geometric shapes and images are central to many tasks in geometry processing, computer …
Maks Ovsjanikov
,
Etienne Corman
,
Michael M. Bronstein
,
Emanuele Rodolà
,
Mirela Ben-Chen
,
Leo Guibas
,
Frederic Chazal
,
Alex M. Bronstein
Cite
URL
Realistic Photometric Stereo Using Partial Differential Irradiance Equation Ratios
CAG
Shape from shading with multiple light sources is an active research area and a diverse range of approaches have been proposed in the …
Roberto Mecca
,
Emanuele Rodolà
,
Daniel Cremers
Cite
Point-wise map recovery and refinement from functional correspondence
VMV 2015
Since their introduction in the shape analysis community, functional maps have met with considerable success due to their ability to …
Emanuele Rodolà
,
Michael Moeller
,
Daniel Cremers
Cite
PDF
Best Paper Award
arXiv
Fast and Accurate Surface Alignment Through an Isometry-Enforcing Game
PR
Surface registration is often performed as a two step process. A feature matching scheme is first adopted to find a coarse initial …
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
A Simple and Effective Relevance-Based Point Sampling for 3D Shapes
PRL
The surface of natural or human-made objects usually comprises a collection of distinct regions characterized by different features. …
Emanuele Rodolà
,
Andrea Albarelli
,
Daniel Cremers
,
Andrea Torsello
Cite
Analysis of surface parametrizations for modern photometric stereo modeling
QCAV
Tridimensional shape recovery based on Photometric Stereo (PS) recently received a strong improvement due to new mathematical models …
Roberto Mecca
,
Emanuele Rodolà
,
Daniel Cremers
Cite
PDF
URL
Adopting an unconstrained ray model in light-field cameras for 3D shape reconstruction
CVPR 2015
Due to their recent availability as off-the-shelf commercial devices, light-field cameras has gathered increasing attention from both …
Filippo Bergamasco
,
Andrea Albarelli
,
Luca Cosmo
,
Andrea Torsello
,
Emanuele Rodolà
,
Daniel Cremers
Cite
PDF
Learning similarities for rigid and non-rigid object detection
3DV 2014
In this paper, we propose an optimization method for estimating the parameters that typically appear in graph-theoretical formulations …
Asako Kanezaki
,
Emanuele Rodolà
,
Daniel Cremers
,
Tatsuya Harada
Cite
URL
Optimal Intrinsic Descriptors for Non-Rigid Shape Analysis
BMVC 2014
We propose novel point descriptors for 3D shapes with the potential to match two shapes of the same object under natural deformations. …
Thomas Windheuser
,
Matthias Vestner
,
Emanuele Rodolà
,
Rudolf Triebel
,
Daniel Cremers
Cite
PDF
URL
Anisotropic Laplace-Beltrami operators for shape analysis
NORDIA 2014
This paper introduces an anisotropic Laplace-Beltrami operator for shape analysis. While keeping useful properties of the standard …
Mathieu Andreux
,
Emanuele Rodolà
,
Mathieu Aubry
,
Daniel Cremers
Cite
PDF
Robust Region Detection via Consensus Segmentation of Deformable Shapes
CGF (Proc. SGP 2014)
We consider the problem of stable region detection and segmentation of deformable shapes. We pursue this goal by determining a …
Emanuele Rodolà
,
Samuel Rota Bulo
,
Daniel Cremers
Cite
PDF
URL
Dense non-rigid shape correspondence using random forests
CVPR 2014
We propose a shape matching method that produces dense correspondences tuned to a specific class of shapes and deformations. In a …
Emanuele Rodolà
,
Samuel Rota Bulo
,
Thomas Windheuser
,
Matthias Vestner
,
Daniel Cremers
Cite
PDF
URL
Elastic net constraints for shape matching
ICCV 2013
We consider a parametrized relaxation of the widely adopted quadratic assignment problem (QAP) formulation for minimum distortion …
Emanuele Rodolà
,
Andrea Torsello
,
Tatsuya Harada
,
Yasuo Kuniyoshi
,
Daniel Cremers
Cite
PDF
URL
Efficient Shape Matching using Vector Extrapolation
BMVC 2013
We propose the adoption of a vector extrapolation technique to accelerate convergence of correspondence problems under the quadratic …
Emanuele Rodolà
,
Tatsuya Harada
,
Yasuo Kuniyoshi
,
Daniel Cremers
Cite
PDF
URL
Can a fully unconstrained imaging model be applied effectively to central cameras?
CVPR 2013
Traditional camera models are often the result of a compromise between the ability to account for non-linearities in the image …
Filippo Bergamasco
,
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
PDF
URL
Stable and Fast Techniques for Unambiguous Compound Phase Coding
IVC
Phase shift methods have proven to be very robust and accurate for photometric 3D reconstruction. One problem of these approaches is …
Andrea Torsello
,
Andrea Albarelli
,
Emanuele Rodolà
Cite
URL
A Scale Independent Selection Process for 3D Object Recognition in Cluttered Scenes
IJCV
During the last years a wide range of algorithms and devices have been made available to easily acquire range images. The increasing …
Emanuele Rodolà
,
Andrea Albarelli
,
Filippo Bergamasco
,
Andrea Torsello
Cite
URL
A game-theoretic approach to deformable shape matching
CVPR 2012
We consider the problem of minimum distortion intrinsic correspondence between deformable shapes, many useful formulations of which …
Emanuele Rodolà
,
Alex M. Bronstein
,
Andrea Albarelli
,
Filippo Bergamasco
,
Andrea Torsello
Cite
PDF
URL
Imposing Semi-local Geometric Constraints for Accurate Correspondences Selection in Structure from Motion: a Game-Theoretic Perspective
IJCV
Most Structure from Motion pipelines are based on the iterative refinement of an initial batch of feature correspondences. Typically …
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
PDF
URL
Rune-tag: A high accuracy fiducial marker with strong occlusion resilience
CVPR 2011
Over the last decades fiducial markers have provided widely adopted tools to add reliable model-based features into an otherwise …
Filippo Bergamasco
,
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
PDF
URL
GitHub
Multiview registration via graph diffusion of dual quaternions
CVPR 2011
Surface registration is a fundamental step in the reconstruction of three-dimensional objects. While there are several fast and …
Andrea Torsello
,
Emanuele Rodolà
,
Andrea Albarelli
Cite
PDF
URL
Sampling relevant points for surface registration
3DPVT 2011
Surface registration is a fundamental step in the reconstruction of three-dimensional objects. This is typically a two-step process …
Andrea Torsello
,
Emanuele Rodolà
,
Andrea Albarelli
Cite
PDF
URL
A Non-Cooperative Game for 3D Object Recognition in Cluttered Scenes
3DPVT 2011
During the last few years a wide range of algorithms and devices have been made available to easily acquire range images. To this …
Andrea Albarelli
,
Emanuele Rodolà
,
Filippo Bergamasco
,
Andrea Torsello
Cite
PDF
URL
Loosely distinctive features for robust surface alignment
ECCV 2010
Many successful feature detectors and descriptors exist for 2D intensity images. However, obtaining the same effectiveness in the …
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
PDF
URL
Robust camera calibration using inaccurate targets
BMVC 2010
Accurate intrinsic camera calibration is essential to any computer vision task that involves image based measurements. Given its …
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
PDF
URL
A game-theoretic approach to the enforcement of global consistency in multi-view feature matching
SSPR 2010
In this paper we introduce a robust matching technique that allows to operate a very accurate selection of corresponding feature points …
Emanuele Rodolà
,
Andrea Albarelli
,
Andrea Torsello
Cite
PDF
URL
Robust figure extraction on textured background: a game-theoretic approach
ICPR 2010
Feature-based image matching relies on the assumption that the features contained in the model are distinctive enough. When both model …
Andrea Albarelli
,
Emanuele Rodolà
,
Alberto Cavallarin
,
Andrea Torsello
Cite
PDF
URL
A Game-Theoretic Approach to Robust Selection of Multi-View Point Correspondence
ICPR 2010
In this paper we introduce a robust matching technique that allows very accurate selection of corresponding feature points from …
Emanuele Rodolà
,
Andrea Albarelli
,
Andrea Torsello
Cite
URL
PDF
A game-theoretic approach to fine surface registration without initial motion estimation
CVPR 2010
Surface registration is a fundamental step in the reconstruction of three-dimensional objects. This is typically a two step process …
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
URL
PDF
Robust game-theoretic inlier selection for bundle adjustment
3DPVT 2010
Bundle Adjustment is a widely adopted self-calibration technique that allows to estimate scene structure and camera parameters at once. …
Andrea Albarelli
,
Emanuele Rodolà
,
Andrea Torsello
Cite
PDF
Best Student Paper Award
Fast 3D surface reconstruction by unambiguous compound phase coding
3DIM 2009
Phase shift methods have proven to be very robust and accurate for photometric 3D reconstruction. One problem of these approaches is …
Andrea Albarelli
,
Emanuele Rodolà
,
Samuel Rota Bulo
,
Andrea Torsello
Cite
URL
PDF
Cite
×