12 citations · 28 across the 28 of their papers we have counts for
34 papers · 1 filter
GigaBench: Benchmarking Learnable Representations for Gigapixel Image Compression and Super-Resolution
Matteo Fusconi, Alex Costanzino, Pierluigi Zama Ramirez +1
Learnable Representations (LRs) can fit parametric families of functions to diverse kinds of signals. These emergent neural-native data formats are gathering interest in the scient…
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…
Modulate-and-Map: Crossmodal Feature Mapping with Cross-View Modulation for 3D Anomaly Detection
Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti +1
We present ModMap, a natively multiview and multimodal framework for 3D anomaly detection and segmentation. Unlike existing methods that process views independently, our method dra…
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…
Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training
Andrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti +2
Recent advances in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in understanding both images and 3D data, yet these modalities face inherent limitati…
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…
Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions
Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi
We present a novel approach designed to address the complexities posed by challenging, out-of-distribution data in the single-image depth estimation task. Starting with images that…
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…
Learning Depth Estimation for Transparent and Mirror Surfaces
Alex Costanzino, Pierluigi Zama Ramirez, Matteo Poggi +3
Inferring the depth of transparent or mirror (ToM) surfaces represents a hard challenge for either sensors, algorithms, or deep networks. We propose a simple pipeline for learning…
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…
Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces
Pierluigi Zama Ramirez, Alex Costanzino, Fabio Tosi +4
Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open…
Self-Distillation for Unsupervised 3D Domain Adaptation
Adriano Cardace, Riccardo Spezialetti, Pierluigi Zama Ramirez +2
Point cloud classification is a popular task in 3D vision. However, previous works, usually assume that point clouds at test time are obtained with the same procedure or sensor as…
Cross-Spectral Neural Radiance Fields
Matteo Poggi, Pierluigi Zama Ramirez, Fabio Tosi +3
We propose X-NeRF, a novel method to learn a Cross-Spectral scene representation given images captured from cameras with different light spectrum sensitivity, based on the Neural R…
RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation
Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi +3
We address the problem of registering synchronized color (RGB) and multi-spectral (MS) images featuring very different resolution by solving stereo matching correspondences. Purpos…
Open Challenges in Deep Stereo: the Booster Dataset
Pierluigi Zama Ramirez, Fabio Tosi, Matteo Poggi +3
We present a novel high-resolution and challenging stereo dataset framing indoor scenes annotated with dense and accurate ground-truth disparities. Peculiar to our dataset is the p…