16 citations · 47 across the 25 of their papers we have counts for
29 papers · 1 filter
CoordFormer: Give Me Any Coordinates and I Will Give You Labels
Iacopo Curti, Pierluigi Zama Ramirez, Alioscia Petrelli +1
Semantic segmentation on very-high-resolution images remains challenging due to the high computational cost and the difficulty of capturing fine-grained details. We propose CoordFo…
Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations
Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti +1
Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks, yet facing a spectral dilemma: periodic activat…
SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark
Alex Costanzino, Pierluigi Zama Ramirez, Luigi Lella +4
We propose SiM3D, the first benchmark considering the integration of multiview and multimodal information for comprehensive 3D anomaly detection and segmentation (ADS), where the t…
NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
Pierluigi Zama Ramirez, Fabio Tosi, Luigi Di Stefano +36
This paper reports on the NTIRE 2025 challenge on HR Depth From images of Specular and Transparent surfaces, held in conjunction with the New Trends in Image Restoration and Enhanc…
Weight Space Representation Learning on Diverse NeRF Architectures
Francesco Ballerini, Pierluigi Zama Ramirez, Luigi Di Stefano +1
Neural Radiance Fields (NeRFs) have emerged as a groundbreaking paradigm for representing 3D objects and scenes by encoding shape and appearance information into the weights of a n…
Learning to Be a Transformer to Pinpoint Anomalies
Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti +1
To efficiently deploy strong, often pre-trained feature extractors, recent Industrial Anomaly Detection and Segmentation (IADS) methods process low-resolution images, e.g., 224x224…
LLaNA: Large Language and NeRF Assistant
Andrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti +2
Multimodal Large Language Models (MLLMs) have demonstrated an excellent understanding of images and 3D data. However, both modalities have shortcomings in holistically capturing th…
Connecting NeRFs, Images, and Text
Francesco Ballerini, Pierluigi Zama Ramirez, Roberto Mirabella +2
Neural Radiance Fields (NeRFs) have emerged as a standard framework for representing 3D scenes and objects, introducing a novel data type for information exchange and storage. Conc…
Test Time Training for Industrial Anomaly Segmentation
Alex Costanzino, Pierluigi Zama Ramirez, Mirko Del Moro +4
Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control. While existing methods excel in generating anomaly scores for each pixel, practical application…
Deep Learning on Object-centric 3D Neural Fields
Pierluigi Zama Ramirez, Luca De Luigi, Daniele Sirocchi +5
In recent years, Neural Fields (NFs) have emerged as an effective tool for encoding diverse continuous signals such as images, videos, audio, and 3D shapes. When applied to 3D data…
Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping
Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti +1
The paper explores the industrial multimodal Anomaly Detection (AD) task, which exploits point clouds and RGB images to localize anomalies. We introduce a novel light and fast fram…
Neural Processing of Tri-Plane Hybrid Neural Fields
Adriano Cardace, Pierluigi Zama Ramirez, Francesco Ballerini +3
Driven by the appealing properties of neural fields for storing and communicating 3D data, the problem of directly processing them to address tasks such as classification and part…
Looking at words and points with attention: a benchmark for text-to-shape coherence
Andrea Amaduzzi, Giuseppe Lisanti, Samuele Salti +1
While text-conditional 3D object generation and manipulation have seen rapid progress, the evaluation of coherence between generated 3D shapes and input textual descriptions lacks…
ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects
Marco Toschi, Riccardo De Matteo, Riccardo Spezialetti +3
In this paper, we focus on the problem of rendering novel views from a Neural Radiance Field (NeRF) under unobserved light conditions. To this end, we introduce a novel dataset, du…
Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation
Adriano Cardace, Pierluigi Zama Ramirez, Samuele Salti +1
3D semantic segmentation is a critical task in many real-world applications, such as autonomous driving, robotics, and mixed reality. However, the task is extremely challenging due…
Deep Learning on Implicit Neural Representations of Shapes
Luca De Luigi, Adriano Cardace, Riccardo Spezialetti +3
Implicit Neural Representations (INRs) have emerged in the last few years as a powerful tool to encode continuously a variety of different signals like images, videos, audio and 3D…
Learning Good Features to Transfer Across Tasks and Domains
Pierluigi Zama Ramirez, Adriano Cardace, Luca De Luigi +3
Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to…
ScanNeRF: a Scalable Benchmark for Neural Radiance Fields
Luca De Luigi, Damiano Bolognini, Federico Domeniconi +3
In this paper, we propose the first-ever real benchmark thought for evaluating Neural Radiance Fields (NeRFs) and, in general, Neural Rendering (NR) frameworks. We design and imple…
Learning the Space of Deep Models
Gianluca Berardi, Luca De Luigi, Samuele Salti +1
Embedding of large but redundant data, such as images or text, in a hierarchy of lower-dimensional spaces is one of the key features of representation learning approaches, which no…
Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation
Adriano Cardace, Luca De Luigi, Pierluigi Zama Ramirez +2
Although recent semantic segmentation methods have made remarkable progress, they still rely on large amounts of annotated training data, which are often infeasible to collect in t…
SAFFIRE: System for Autonomous Feature Filtering and Intelligent ROI Estimation
Marco Boschi, Luigi Di Stefano, Martino Alessandrini
This work introduces a new framework, named SAFFIRE, to automatically extract a dominant recurrent image pattern from a set of image samples. Such a pattern shall be used to elimin…
Boosting Object Recognition in Point Clouds by Saliency Detection
Marlon Marcon, Riccardo Spezialetti, Samuele Salti +2
Object recognition in 3D point clouds is a challenging task, mainly when time is an important factor to deal with, such as in industrial applications. Local descriptors are an amen…
Learning an Effective Equivariant 3D Descriptor Without Supervision
Riccardo Spezialetti, Samuele Salti, Luigi Di Stefano
Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typically addressed by matching local descriptors. Recently, a few attempts at applying…
Semi-Automatic Labeling for Deep Learning in Robotics
Daniele De Gregorio, Alessio Tonioni, Gianluca Palli +1
In this paper, we propose Augmented Reality Semi-automatic labeling (ARS), a semi-automatic method which leverages on moving a 2D camera by means of a robot, proving precise camera…