D. Boscaini

发表

Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs

Jonathan Masci, Michael M. Bronstein, Jan Svoboda, 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning

M. Bronstein, E. Rodolà, P. Gainza, 2019, Nature Methods.

Supervised Tractogram Filtering using Geometric Deep Learning

Jonathan Masci, L. Petit, P. Avesani, 2022, Medical Image Anal..

Global-Local Graph Neural Networks for Node-Classification

Wojciech Zaremba, Joan Bruna, M. Bronstein, 2022 .

Geometric Deep Learning for Shape Analysis

Davide Boscaini, D. Boscaini, 2017 .

Learning class‐specific descriptors for deformable shapes using localized spectral convolutional networks

Pierre Vandergheynst, Jonathan Masci, Michael M. Bronstein, 2015, SGP '15.

Anisotropic Diffusion Descriptors

Daniel Cremers, Jonathan Masci, Michael M. Bronstein, 2016, Comput. Graph. Forum.

Geodesic Convolutional Neural Networks on Riemannian Manifolds

Pierre Vandergheynst, Jonathan Masci, Michael M. Bronstein, 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

ShapeNet: Convolutional Neural Networks on Non-Euclidean Manifolds pdf

Pierre Vandergheynst, Jonathan Masci, Michael M. Bronstein, 2015, ArXiv.

Coulomb Shapes: Using Electrostatic Forces for Deformation-invariant Shape Representation

Michael M. Bronstein, Ramunas Girdziusas, Davide Boscaini, 2014, 3DOR@Eurographics.

Learning shape correspondence with anisotropic convolutional neural networks

Jonathan Masci, Michael M. Bronstein, Emanuele Rodolà, 2016, NIPS.

Learning General and Distinctive 3D Local Deep Descriptors for Point Cloud Registration

D. Boscaini, F. Poiesi, 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Distinctive 3D local deep descriptors pdf

Fabio Poiesi, Davide Boscaini, D. Boscaini, 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

Joint Supervised and Self-Supervised Learning for 3D Real World Challenges pdf

Tatiana Tommasi, Davide Boscaini, Antonio Alliegro, 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

A sparse coding approach for local-to-global 3D shape description

Umberto Castellani, Davide Boscaini, U. Castellani, 2014, The Visual Computer.

Structured Domain Adaptation for 3D Keypoint Estimation

Elisa Ricci, Barbara Caputo, Massimiliano Mancini, 2019, 2019 International Conference on 3D Vision (3DV).

Self-Supervised Generalization on Real-World 3D Point Clouds

T. Tommasi, P. Torino, D. Boscaini, 2019 .

Geometric deep learning

Jonathan Masci, Michael M. Bronstein, Hao Li, 2016, SIGGRAPH ASIA Courses.

Shape‐from‐Operator: Recovering Shapes from Intrinsic Operators

Davide Eynard, Michael M. Bronstein, Davide Boscaini, 2015, Comput. Graph. Forum.

Local Signature Quantization by Sparse Coding

Umberto Castellani, Davide Boscaini, U. Castellani, 2013, 3DOR@Eurographics.

Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation

D. Boscaini, F. Poiesi, Jaime Corsetti, 2023, ArXiv.

The MONET dataset: Multimodal drone thermal dataset recorded in rural scenarios

M. L. Mekhalfi, D. Boscaini, D. Abate, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Shape-from-intrinsic operator pdf

Davide Eynard, Michael M. Bronstein, Davide Boscaini, 2014, ArXiv.

PatchMixer: Rethinking network design to boost generalization for 3D point cloud understanding

D. Boscaini, F. Poiesi, 2023, Image Vis. Comput..

Generalisable and distinctive 3D local deep descriptors for point cloud registration

D. Boscaini, Fabio Poiesi, 2021, ArXiv.

Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection

M. L. Mekhalfi, D. Boscaini, Fabio Poiesi, 2023, BMVC.

Tractogram filtering of anatomically non-plausible fibers with geometric deep learning

Jonathan Masci, L. Petit, P. Avesani, 2020, MICCAI.

Learning interaction patterns from surface representations of protein structure.

M. Bronstein, P. Gainza, Freyr Sverrisson, 2019 .