arXiv subjects

Stefano Ghidoni

Publications and source records attributed to Stefano Ghidoni.

At least 19 recordsLinked to original sources

arXiv2026

Paparazzo: Active Mapping of Moving 3D Objects

Current 3D mapping pipelines generally assume static environments, which limits their ability to accurately capture and reconstruct moving objects. To address this limitation, we introduce the novel task of active mapping of moving objects, in which a mapping agent must plan its trajectory while compensating for the object's motion. Our approach, Paparazzo, provides a learning-free solution that robustly predicts the target's trajectory and identifies the most informative viewpoints from which to observe it, to plan its own path. We also contribute a comprehensive benchmark designed for this new task. Through extensive experiments, we show that Paparazzo significantly improves 3D reconstruction completeness and accuracy compared to several strong baselines, marking an important step toward dynamic scene understanding. Project page: https://davidea97.github.io/paparazzo-page/

cs.CV↗

arXiv2025

SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering

Accurate 3D human pose estimation is fundamental for applications such as augmented reality and human-robot interaction. State-of-the-art multi-view methods learn to fuse predictions across views by training on large annotated datasets, leading to poor generalization when the test scenario differs. To overcome these limitations, we propose SkelSplat, a novel framework for multi-view 3D human pose estimation based on differentiable Gaussian rendering. Human pose is modeled as a skeleton of 3D Gaussians, one per joint, optimized via differentiable rendering to enable seamless fusion of arbitrary camera views without 3D ground-truth supervision. Since Gaussian Splatting was originally designed for dense scene reconstruction, we propose a novel one-hot encoding scheme that enables independent optimization of human joints. SkelSplat outperforms approaches that do not rely on 3D ground truth in Human3.6M and CMU, while reducing the cross-dataset error up to 47.8% compared to learning-based methods. Experiments on Human3.6M-Occ and Occlusion-Person demonstrate robustness to occlusions, without scenario-specific fine-tuning. Our project page is available here: https://skelsplat.github.io.

cs.CV↗

arXiv2025

Leveraging Multi-View Weak Supervision for Occlusion-Aware Multi-Human Parsing

Multi-human parsing is the task of segmenting human body parts while associating each part to the person it belongs to, combining instance-level and part-level information for fine-grained human understanding. In this work, we demonstrate that, while state-of-the-art approaches achieved notable results on public datasets, they struggle considerably in segmenting people with overlapping bodies. From the intuition that overlapping people may appear separated from a different point of view, we propose a novel training framework exploiting multi-view information to improve multi-human parsing models under occlusions. Our method integrates such knowledge during the training process, introducing a novel approach based on weak supervision on human instances and a multi-view consistency loss. Given the lack of suitable datasets in the literature, we propose a semi-automatic annotation strategy to generate human instance segmentation masks from multi-view RGB+D data and 3D human skeletons. The experiments demonstrate that the approach can achieve up to a 4.20\% relative improvement on human parsing over the baseline model in occlusion scenarios.

cs.CV↗

arXiv2025

Calib3R: Hand-Eye Calibration and 3D Metric-Scaled Scene Reconstruction with 3D Foundation Models

Robots often rely on RGB images for tasks like manipulation. However, reliable interaction typically requires a 3D scene representation that is metric-scaled and aligned with the robot reference frame. This depends on accurate hand-eye calibration and dense 3D reconstruction, tasks usually treated separately, despite both relying on geometric correspondences from RGB data. Traditional calibration techniques needs patterns, while RGB-based reconstruction yields 3D geometry with an unknown scale in an arbitrary frame. Multi-camera setups add further complexity, as data must be expressed in a shared reference frame. We present Calib3R, a patternless method that jointly performs hand-eye calibration and metric-scaled 3D reconstruction via unified optimization. Calib3R handles single- and multi-camera setups on robot arms. It builds on a 3D foundation model to extract pointmaps from RGB images, which are combined with robot poses to reconstruct a scaled 3D scene aligned with the robot base reference frame. Experiments on diverse datasets show that Calib3R achieves accurate calibration with less than 10 images, outperforming patternless and pattern-based methods.

cs.RO↗

arXiv2025

Stress-Aware Resilient Neural Training

This paper introduces Stress-Aware Learning, a resilient neural training paradigm in which deep neural networks dynamically adjust their optimization behavior - whether under stable training regimes or in settings with uncertain dynamics - based on the concept of Temporary (Elastic) and Permanent (Plastic) Deformation, inspired by structural fatigue in materials science. To instantiate this concept, we propose Plastic Deformation Optimizer, a stress-aware mechanism that injects adaptive noise into model parameters whenever an internal stress signal - reflecting stagnation in training loss and accuracy - indicates persistent optimization difficulty. This enables the model to escape sharp minima and converge toward flatter, more generalizable regions of the loss landscape. Experiments across six architectures, four optimizers, and seven vision benchmarks demonstrate improved robustness and generalization with minimal computational overhead. The code and 3D visuals will be available on GitHub: https://github.com/Stress-Aware-Learning/SAL.

cs.LG↗

arXiv2025

Unit-Based Histopathology Tissue Segmentation via Multi-Level Feature Representation

We propose UTS, a unit-based tissue segmentation framework for histopathology that classifies each fixed-size 32 * 32 tile, rather than each pixel, as the segmentation unit. This approach reduces annotation effort and improves computational efficiency without compromising accuracy. To implement this approach, we introduce a Multi-Level Vision Transformer (L-ViT), which benefits the multi-level feature representation to capture both fine-grained morphology and global tissue context. Trained to segment breast tissue into three categories (infiltrating tumor, non-neoplastic stroma, and fat), UTS supports clinically relevant tasks such as tumor-stroma quantification and surgical margin assessment. Evaluated on 386,371 tiles from 459 H&E-stained regions, it outperforms U-Net variants and transformer-based baselines. Code and Dataset will be available at GitHub.

eess.IV↗

arXiv2025

DepViT-CAD: Deployable Vision Transformer-Based Cancer Diagnosis in Histopathology

Accurate and timely cancer diagnosis from histopathological slides is vital for effective clinical decision-making. This paper introduces DepViT-CAD, a deployable AI system for multi-class cancer diagnosis in histopathology. At its core is MAViT, a novel Multi-Attention Vision Transformer designed to capture fine-grained morphological patterns across diverse tumor types. MAViT was trained on expert-annotated patches from 1008 whole-slide images, covering 11 diagnostic categories, including 10 major cancers and non-tumor tissue. DepViT-CAD was validated on two independent cohorts: 275 WSIs from The Cancer Genome Atlas and 50 routine clinical cases from pathology labs, achieving diagnostic sensitivities of 94.11% and 92%, respectively. By combining state-of-the-art transformer architecture with large-scale real-world validation, DepViT-CAD offers a robust and scalable approach for AI-assisted cancer diagnostics. To support transparency and reproducibility, software and code will be made publicly available at GitHub.

eess.IV↗

arXiv2025

VeLU: Variance-enhanced Learning Unit for Deep Neural Networks

Activation functions play a critical role in deep neural networks by shaping gradient flow, optimization stability, and generalization. While ReLU remains widely used due to its simplicity, it suffers from gradient sparsity and dead-neuron issues and offers no adaptivity to input statistics. Smooth alternatives such as Swish and GELU improve gradient propagation but still apply a fixed transformation regardless of the activation distribution. In this paper, we propose VeLU, a Variance-enhanced Learning Unit that introduces variance-aware and distributionally aligned nonlinearity through a principled combination of ArcTan-ArcSin transformations, adaptive scaling, and Wasserstein-2 regularization (Optimal Transport). This design enables VeLU to modulate its response based on local activation variance, mitigate internal covariate shift at the activation level, and improve training stability without adding learnable parameters or architectural overhead. Extensive experiments across six deep neural networks show that VeLU outperforms ReLU, ReLU6, Swish, and GELU on 12 vision benchmarks. The implementation of VeLU is publicly available in GitHub.

cs.LG↗

arXiv2024

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. Current world models typically cannot directly and explicitly imitate the actual environment in front of a robot, often resulting in unrealistic behaviors and hallucinations that make them unsuitable for real-world robotics applications. To overcome those challenges, we propose to rethink robot world models as learnable digital twins. We introduce DreMa, a new approach for constructing digital twins automatically using learned explicit representations of the real world and its dynamics, bridging the gap between traditional digital twins and world models. DreMa replicates the observed world and its structure by integrating Gaussian Splatting and physics simulators, allowing robots to imagine novel configurations of objects and to predict the future consequences of robot actions thanks to its compositionality. We leverage this capability to generate new data for imitation learning by applying equivariant transformations to a small set of demonstrations. Our evaluations across various settings demonstrate significant improvements in accuracy and robustness by incrementing actions and object distributions, reducing the data needed to learn a policy and improving the generalization of the agents. As a highlight, we show that a real Franka Emika Panda robot, powered by DreMa's imagination, can successfully learn novel physical tasks from just a single example per task variation (one-shot policy learning). Our project page can be found in: https://dreamtomanipulate.github.io/.

cs.RO↗

arXiv2024

MEMROC: Multi-Eye to Mobile RObot Calibration

This paper presents MEMROC (Multi-Eye to Mobile RObot Calibration), a novel motion-based calibration method that simplifies the process of accurately calibrating multiple cameras relative to a mobile robot's reference frame. MEMROC utilizes a known calibration pattern to facilitate accurate calibration with a lower number of images during the optimization process. Additionally, it leverages robust ground plane detection for comprehensive 6-DoF extrinsic calibration, overcoming a critical limitation of many existing methods that struggle to estimate the complete camera pose. The proposed method addresses the need for frequent recalibration in dynamic environments, where cameras may shift slightly or alter their positions due to daily usage, operational adjustments, or vibrations from mobile robot movements. MEMROC exhibits remarkable robustness to noisy odometry data, requiring minimal calibration input data. This combination makes it highly suitable for daily operations involving mobile robots. A comprehensive set of experiments on both synthetic and real data proves MEMROC's efficiency, surpassing existing state-of-the-art methods in terms of accuracy, robustness, and ease of use. To facilitate further research, we have made our code publicly available at https://github.com/davidea97/MEMROC.git.

cs.RO↗

arXiv2024

WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks

Robotic waste sorting poses significant challenges in both perception and manipulation, given the extreme variability of objects that should be recognized on a cluttered conveyor belt. While deep learning has proven effective in solving complex tasks, the necessity for extensive data collection and labeling limits its applicability in real-world scenarios like waste sorting. To tackle this issue, we introduce a data augmentation method based on a novel GAN architecture called wasteGAN. The proposed method allows to increase the performance of semantic segmentation models, starting from a very limited bunch of labeled examples, such as few as 100. The key innovations of wasteGAN include a novel loss function, a novel activation function, and a larger generator block. Overall, such innovations helps the network to learn from limited number of examples and synthesize data that better mirrors real-world distributions. We then leverage the higher-quality segmentation masks predicted from models trained on the wasteGAN synthetic data to compute semantic-aware grasp poses, enabling a robotic arm to effectively recognizing contaminants and separating waste in a real-world scenario. Through comprehensive evaluation encompassing dataset-based assessments and real-world experiments, our methodology demonstrated promising potential for robotic waste sorting, yielding performance gains of up to 5.8\% in picking contaminants. The project page is available at https://github.com/bach05/wasteGAN.git

cs.RO↗

arXiv2024

SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation

Out-of-Distribution (OOD) detection in computer vision is a crucial research area, with related benchmarks playing a vital role in assessing the generalizability of models and their applicability in real-world scenarios. However, existing OOD benchmarks in the literature suffer from two main limitations: (1) they often overlook semantic shift as a potential challenge, and (2) their scale is limited compared to the large datasets used to train modern models. To address these gaps, we introduce SOOD-ImageNet, a novel dataset comprising around 1.6M images across 56 classes, designed for common computer vision tasks such as image classification and semantic segmentation under OOD conditions, with a particular focus on the issue of semantic shift. We ensured the necessary scalability and quality by developing an innovative data engine that leverages the capabilities of modern vision-language models, complemented by accurate human checks. Through extensive training and evaluation of various models on SOOD-ImageNet, we showcase its potential to significantly advance OOD research in computer vision. The project page is available at https://github.com/bach05/SOODImageNet.git.

cs.CV↗

arXiv2024

Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose Estimation

Robust 3D human pose estimation is crucial to ensure safe and effective human-robot collaboration. Accurate human perception,however, is particularly challenging in these scenarios due to strong occlusions and limited camera viewpoints. Current 3D human pose estimation approaches are rather vulnerable in such conditions. In this work we present a novel approach for robust 3D human pose estimation in the context of human-robot collaboration. Instead of relying on noisy 2D features triangulation, we perform multi-view fusion on 3D skeletons provided by absolute monocular methods. Accurate 3D pose estimation is then obtained via reprojection error optimization, introducing limbs length symmetry constraints. We evaluate our approach on the public dataset Human3.6M and on a novel version Human3.6M-Occluded, derived adding synthetic occlusions on the camera views with the purpose of testing pose estimation algorithms under severe occlusions. We further validate our method on real human-robot collaboration workcells, in which we strongly surpass current 3D human pose estimation methods. Our approach outperforms state-of-the-art multi-view human pose estimation techniques and demonstrates superior capabilities in handling challenging scenarios with strong occlusions, representing a reliable and effective solution for real human-robot collaboration setups.

cs.CV↗

arXiv2024

Multi-Camera Hand-Eye Calibration for Human-Robot Collaboration in Industrial Robotic Workcells

In industrial scenarios, effective human-robot collaboration relies on multi-camera systems to robustly monitor human operators despite the occlusions that typically show up in a robotic workcell. In this scenario, precise localization of the person in the robot coordinate system is essential, making the hand-eye calibration of the camera network critical. This process presents significant challenges when high calibration accuracy should be achieved in short time to minimize production downtime, and when dealing with extensive camera networks used for monitoring wide areas, such as industrial robotic workcells. Our paper introduces an innovative and robust multi-camera hand-eye calibration method, designed to optimize each camera's pose relative to both the robot's base and to each other camera. This optimization integrates two types of key constraints: i) a single board-to-end-effector transformation, and ii) the relative camera-to-camera transformations. We demonstrate the superior performance of our method through comprehensive experiments employing the METRIC dataset and real-world data collected on industrial scenarios, showing notable advancements over state-of-the-art techniques even using less than 10 images. Additionally, we release an open-source version of our multi-camera hand-eye calibration algorithm at https://github.com/davidea97/Multi-Camera-Hand-Eye-Calibration.git.

cs.RO↗

arXiv2024

Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models

The ability of a robot to pick an object, known as robot grasping, is crucial for several applications, such as assembly or sorting. In such tasks, selecting the right target to pick is as essential as inferring a correct configuration of the gripper. A common solution to this problem relies on semantic segmentation models, which often show poor generalization to unseen objects and require considerable time and massive data to be trained. To reduce the need for large datasets, some grasping pipelines exploit few-shot semantic segmentation models, which are capable of recognizing new classes given a few examples. However, this often comes at the cost of limited performance and fine-tuning is required to be effective in robot grasping scenarios. In this work, we propose to overcome all these limitations by combining the impressive generalization capability reached by foundation models with a high-performing few-shot classifier, working as a score function to select the segmentation that is closer to the support set. The proposed model is designed to be embedded in a grasp synthesis pipeline. The extensive experiments using one or five examples show that our novel approach overcomes existing performance limitations, improving the state of the art both in few-shot semantic segmentation on the Graspnet-1B (+10.5% mIoU) and Ocid-grasp (+1.6% AP) datasets, and real-world few-shot grasp synthesis (+21.7% grasp accuracy). The project page is available at: https://leobarcellona.github.io/showandgrasp.github.io/

cs.RO↗

arXiv2020

Deep learning and hand-crafted features for virus image classification

In this work, we present an ensemble of descriptors for the classification of transmission electron microscopy images of viruses. We propose to combine handcrafted and deep learning approaches for virus image classification. The set of handcrafted is mainly based on Local Binary Pattern variants, for each descriptor a different Support Vector Machine is trained, then the set of classifiers is combined by sum rule. The deep learning approach is a densenet201 pretrained on ImageNet and then tuned in the virus dataset, the net is used as features extractor for feeding another Support Vector Machine, in particular the last average pooling layer is used as feature extractor. Finally, classifiers trained on handcrafted features and classifier trained on deep learning features are combined by sum rule. The proposed fusion strongly boosts the performance obtained by each stand-alone approach, obtaining state of the art performance.

cs.CV↗

arXiv2020

Comparisons among different stochastic selection of activation layers for convolutional neural networks for healthcare

Classification of biological images is an important task with crucial application in many fields, such as cell phenotypes recognition, detection of cell organelles and histopathological classification, and it might help in early medical diagnosis, allowing automatic disease classification without the need of a human expert. In this paper we classify biomedical images using ensembles of neural networks. We create this ensemble using a ResNet50 architecture and modifying its activation layers by substituting ReLUs with other functions. We select our activations among the following ones: ReLU, leaky ReLU, Parametric ReLU, ELU, Adaptive Piecewice Linear Unit, S-Shaped ReLU, Swish , Mish, Mexican Linear Unit, Gaussian Linear Unit, Parametric Deformable Linear Unit, Soft Root Sign (SRS) and others. As a baseline, we used an ensemble of neural networks that only use ReLU activations. We tested our networks on several small and medium sized biomedical image datasets. Our results prove that our best ensemble obtains a better performance than the ones of the naive approaches. In order to encourage the reproducibility of this work, the MATLAB code of all the experiments will be shared at https://github.com/LorisNanni.

cs.CV↗

arXiv2020

RUR53: an Unmanned Ground Vehicle for Navigation, Recognition and Manipulation

This paper proposes RUR53: an Unmanned Ground Vehicle able to autonomously navigate through, identify, and reach areas of interest; and there recognize, localize, and manipulate work tools to perform complex manipulation tasks. The proposed contribution includes a modular software architecture where each module solves specific sub-tasks and that can be easily enlarged to satisfy new requirements. Included indoor and outdoor tests demonstrate the capability of the proposed system to autonomously detect a target object (a panel) and precisely dock in front of it while avoiding obstacles. They show it can autonomously recognize and manipulate target work tools (i.e., wrenches and valve stems) to accomplish complex tasks (i.e., use a wrench to rotate a valve stem). A specific case study is described where the proposed modular architecture lets easy switch to a semi-teleoperated mode. The paper exhaustively describes description of both the hardware and software setup of RUR53, its performance when tests at the 2017 Mohamed Bin Zayed International Robotics Challenge, and the lessons we learned when participating at this competition, where we ranked third in the Gran Challenge in collaboration with the Czech Technical University in Prague, the University of Pennsylvania, and the University of Lincoln (UK).

cs.RO↗