Avatar
Riccardo Marin
For my CV click here

Bio

I am a Post Doctoral researcher, awarded with a Humboldt Post-Doctoral Fellowship, at the University of Tübingen in the Real-Virtual Humans group led by Gerard Pons-Moll.

Previously, I was a post-doc at Sapienza University of Rome in the GLADIA group led by Emanuele Rodolà, leading a work package of SPECGEO ERC project. I followed the University of Verona’s Ph.D program in Computer Science, under the supervision of Umberto Castellani. I graduated in Computer Science and Engineering at University of Verona (2017).

I work on Spectral Shape Analysis, Shape Matching Geometric Deep Learning, and Virtual Humans. My work appears in top level conferences and journals (NeurIPS, IJCV, CGF, 3DV), and also obtained a Best Student Paper Award (3DV 2020).

I served as conference organizer (Volunteer Chair at 3DV 2018 and STAG 2021), as reviewer for several journals and conferences (PAMI, TCVG, CVPR, NeurIPS, ICLR, ICML, IJCV, SIGGRAPH), obtaining four Outstanding Reviewer Awards (CVPR 2022, 3DV 2020 and 2021, ICLR 2021).

I am involved in many fruitful collaborations (Ecole polytechnique (LIX), Max-Planck Institute (MPI), INRIA Strasbourg, Sapienza University of Rome, University College London (UCL), University of Milan, University of Verona), and in projects financed by Google and ERC.

Selected Papers

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 approach is data-driven and adopts for the first time the transformer architecture in the registration task.
Code · Paper
Spectral Shape Recovery and Analysis Via Data-driven Connections

International Journal of Computer Vision
2021

We introduce a novel learning-based method to recover shapes from their Laplacian spectra, based on establishing and exploring connections in a learned latent space. The core of our approach consists in a cycle-consistent module that maps between a learned latent space and sequences of eigenvalues.
Code · Paper
A functional skeleton transfer

ACM on Computer Graphics and Interactive Techniques
2021

We suggest a novel representation for the skeleton properties, namely the functional regressor, which is compact and invariant to different discretizations and poses. We consider our functional regressor a new operator to adopt in intrinsic geometry pipelines for encoding the pose information, paving the way for several new applications.
Code · Paper
Correspondence Learning via Linearly-invariant Embedding

NeurIPS
2020

The proposed pipeline is an extension and a generalization of the functional maps framework. 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.
Code · Paper
Instant recovery of shape from spectrum via latent space connections

3DV - Best Student Paper Award
2020

We introduce the first learning-based method for recovering shapes from Laplacian spectra. Our model consists ofa cycle-consistent module that maps between learned latentvectors of an auto-encoder and sequences of eigenvalues. This module provides an efficient and effective linkage between Laplacian spectrum and geometry.
Code · Paper
Intrinsic/extrinsic embedding for functional remeshing of 3D shapes

Computer & Graphics
2020

We propose a new method that exploits a remeshing-by-matching approach where the observed noisy shape inherits a regular tessellation from a target shape which already satisfies the professional constraints. A fully automatic pipeline is introduced based on a variation of the functional mapping framework. In particular, a new set of basis functions, namely the Coordinates Manifold Harmonics (CMH), is properly designed for this tessellation transfer task.
Code · Paper
High-Resolution Augmentation for Template Based Matching of Human Models

3DV
2019

This augmentation provides an effective workaround for the resolution limitations imposed by the adopted morphable model. The HRA in its global and localized versions represents a novel refinement strategy for surface subdivision methods.
Code · Paper
FARM: Functional automatic registration method for 3D human bodies
Riccardo Marin, S Melzi, E Rodolà, U Castellani

Computer Graphics Forum
2020

We introduce a new method for non-rigid registration of 3D human shapes. Our proposed pipeline builds upon a given parametric model of the human, and makes use of the functional map representation for encoding and inferring shape maps throughout the registration process.
Code · Paper
POP: full Parametric modelling estimation for Occluded People

3DOR
2019

This track provides the first matching evaluation in terms of large connectivity changes between models that come from totally different modeling methods. We provide a dataset of 44 shapes with dense correspondence as obtained by a highly accurate shape registration method (FARM).
Paper
SHREC 2019: Matching Humans with Different Connectivity

3DOR
2019

This track provides the first matching evaluation in terms of large connectivity changes between models that come from totally different modeling methods. We provide a dataset of 44 shapes with dense correspondence as obtained by a highly accurate shape registration method (FARM).
Code · Paper