28 citations · 40 across the 11 of their papers we have counts for
14 papers
Object pop-up: Can we infer 3D objects and their poses from human interactions alone?
Ilya A. Petrov, Riccardo Marin, Julian Chibane +1
The intimate entanglement between objects affordances and human poses is of large interest, among others, for behavioural sciences, cognitive psychology, and Computer Vision commun…
Accelerating Transformer Inference for Translation via Parallel Decoding
Andrea Santilli, Silvio Severino, Emilian Postolache +4
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solv…
Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching
Ramana Sundararaman, Riccardo Marin, Emanuele Rodola +1
In this work we present a novel approach for computing correspondences between non-rigid objects, by exploiting a reduced representation of deformation fields. Different from exist…
Metric Based Few-Shot Graph Classification
Donato Crisostomi, Simone Antonelli, Valentino Maiorca +3
Many modern deep-learning techniques do not work without enormous datasets. At the same time, several fields demand methods working in scarcity of data. This problem is even more c…
Spectral Maps for Learning on Subgraphs
Marco Pegoraro, Riccardo Marin, Arianna Rampini +3
In graph learning, maps between graphs and their subgraphs frequently arise. For instance, when coarsening or rewiring operations are present along the pipeline, one needs to keep…
Interaction Replica: Tracking Human-Object Interaction and Scene Changes From Human Motion
Vladimir Guzov, Julian Chibane, Riccardo Marin +4
Our world is not static and humans naturally cause changes in their environments through interactions, e.g., opening doors or moving furniture. Modeling changes caused by humans is…
Smoothness and effective regularizations in learned embeddings for shape matching
Riccardo Marin, Souhaib Attaiki, Simone Melzi +2
Many innovative applications require establishing correspondences among 3D geometric objects. However, the countless possible deformations of smooth surfaces make shape matching a…
A functional skeleton transfer
Pietro Musoni, Riccardo Marin, Simone Melzi +1
The animation community has spent significant effort trying to ease rigging procedures. This is necessitated because the increasing availability of 3D data makes manual rigging inf…
Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach
Marco Pegoraro, Simone Melzi, Umberto Castellani +2
Many natural shapes have most of their characterizing features concentrated over a few regions in space. For example, humans and animals have distinctive head shapes, while inorgan…
Shape registration in the time of transformers
Giovanni Trappolini, Luca Cosmo, Luca Moschella +3
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 t…
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…
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…
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…
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…