Zobrazeno 1 - 10
of 244
pro vyhledávání: '"Morerio, P."'
Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial noise. In
Externí odkaz:
http://arxiv.org/abs/2412.03453
We present billboard Splatting (BBSplat) - a novel approach for 3D scene representation based on textured geometric primitives. BBSplat represents the scene as a set of optimizable textured planar primitives with learnable RGB textures and alpha-maps
Externí odkaz:
http://arxiv.org/abs/2411.08508
Autor:
Tsesmelis, Theodore, Palmieri, Luca, Khoroshiltseva, Marina, Islam, Adeela, Elkin, Gur, Shahar, Ofir Itzhak, Scarpellini, Gianluca, Fiorini, Stefano, Ohayon, Yaniv, Alali, Nadav, Aslan, Sinem, Morerio, Pietro, Vascon, Sebastiano, Gravina, Elena, Napolitano, Maria Cristina, Scarpati, Giuseppe, Zuchtriegel, Gabriel, Spühler, Alexandra, Fuchs, Michel E., James, Stuart, Ben-Shahar, Ohad, Pelillo, Marcello, Del Bue, Alessio
This paper proposes the RePAIR dataset that represents a challenging benchmark to test modern computational and data driven methods for puzzle-solving and reassembly tasks. Our dataset has unique properties that are uncommon to current benchmarks for
Externí odkaz:
http://arxiv.org/abs/2410.24010
Autor:
Fiorini, Stefano, Bovolenta, Giulia M., Coniglio, Stefano, Ciavotta, Michele, Morerio, Pietro, Parrinello, Michele, Del Bue, Alessio
Graphs and hypergraphs provide powerful abstractions for modeling interactions among a set of entities of interest and have been attracting a growing interest in the literature thanks to many successful applications in several fields. In particular,
Externí odkaz:
http://arxiv.org/abs/2410.06969
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In essence, such
Externí odkaz:
http://arxiv.org/abs/2408.04955
Autor:
Cardenas-Perez, Carlos, Romualdi, Giulio, Elobaid, Mohamed, Dafarra, Stefano, L'Erario, Giuseppe, Traversaro, Silvio, Morerio, Pietro, Del Bue, Alessio, Pucci, Daniele
This paper presents XBG (eXteroceptive Behaviour Generation), a multimodal end-to-end Imitation Learning (IL) system for a whole-body autonomous humanoid robot used in real-world Human-Robot Interaction (HRI) scenarios. The main contribution of this
Externí odkaz:
http://arxiv.org/abs/2406.15833
Autor:
Litrico, Mattia, Talon, Davide, Battiato, Sebastiano, Del Bue, Alessio, Giuffrida, Mario Valerio, Morerio, Pietro
Standard Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target but usually requires simultaneous access to both source and target data. Moreover, UDA approaches commonly assume that source
Externí odkaz:
http://arxiv.org/abs/2404.10574
We present HAHA - a novel approach for animatable human avatar generation from monocular input videos. The proposed method relies on learning the trade-off between the use of Gaussian splatting and a textured mesh for efficient and high fidelity rend
Externí odkaz:
http://arxiv.org/abs/2404.01053
Autor:
Scarpellini, Gianluca, Fiorini, Stefano, Giuliari, Francesco, Morerio, Pietro, Del Bue, Alessio
Reassembly tasks play a fundamental role in many fields and multiple approaches exist to solve specific reassembly problems. In this context, we posit that a general unified model can effectively address them all, irrespective of the input data type
Externí odkaz:
http://arxiv.org/abs/2402.19302
This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single unlabeled targ
Externí odkaz:
http://arxiv.org/abs/2310.02201