activity
20172025
most citedInfinite Feature Selection: A Graph-based Feature Filtering Approach

244 citations · 250 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2025

Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces

Souhail Hadgi, Luca Moschella, Andrea Santilli +5

Recent works have shown that, when trained at scale, uni-modal 2D vision and text encoders converge to learned features that share remarkable structural properties, despite arising…

cs.CV2020

Correspondence Learning via Linearly-invariant Embedding

Riccardo Marin, Marie-Julie Rakotosaona, Simone Melzi +1

In this paper, we propose a fully differentiable pipeline for estimating accurate dense correspondences between 3D point clouds. The proposed pipeline is an extension and a general…

cs.CV2020

High-Resolution Augmentation for Automatic Template-Based Matching of Human Models

Riccardo Marin, Simone Melzi, Emanuele Rodolà +1

We propose a new approach for 3D shape matching of deformable human shapes. Our approach is based on the joint adoption of three different tools: an intrinsic spectral matching pip…

cs.CV2020244 cited

Infinite Feature Selection: A Graph-based Feature Filtering Approach

Giorgio Roffo, Simone Melzi, Umberto Castellani +2

We propose a filtering feature selection framework that considers subsets of features as paths in a graph, where a node is a feature and an edge indicates pairwise (customizable) r…

cs.CV2020

Instant recovery of shape from spectrum via latent space connections

Riccardo Marin, Arianna Rampini, Umberto Castellani +3

We introduce the first learning-based method for recovering shapes from Laplacian spectra. Given an auto-encoder, our model takes the form of a cycle-consistent module to map laten…

cs.CV2018

FARM: Functional Automatic Registration Method for 3D Human Bodies

Riccardo Marin, Simone Melzi, Emanuele Rodolà +1

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 ma…