arXiv subjects

Pietro Morerio

Publications and source records attributed to Pietro Morerio.

At least 19 recordsLinked to original sources

arXiv2026

Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved inconsistencies using offline multi-view aggregation or multi-stage pipelines that decouple exploration, data association, and caption learning, with limited capacity to reason over previously observed objects. In this paper, we introduce a unified, memory-augmented Vision-Language agent that simultaneously handles data association, object captioning, and exploration policy within a single autoregressive framework. The model processes the current RGB observation, a top-down explored map, and an object-level episodic memory serialized into object-level tokens, ensuring persistent object identity and semantic consistency across extended sequences. To train the model in a self-supervised manner, we collect a dataset in photorealistic 3D environments using a disagreement-based policy and a pseudo-captioning model that enforces consistency across multi-view caption histories. Extensive evaluation on a manually annotated object-level test set, demonstrate improvements of up to +11.86% in standard captioning scores and +7.39% in caption self-similarity over baseline models, while enabling scalable performance through a compact scene representation. Code, model weights, and data are available at https://hsp-iit.github.io/epos-vlm/.

cs.CV↗

arXiv2025

CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures

We present a CloseUpAvatar - a novel approach for articulated human avatar representation dealing with more general camera motions, while preserving rendering quality for close-up views. CloseUpAvatar represents an avatar as a set of textured planes with two sets of learnable textures for low and high-frequency detail. The method automatically switches to high-frequency textures only for cameras positioned close to the avatar's surface and gradually reduces their impact as the camera moves farther away. Such parametrization of the avatar enables CloseUpAvatar to adjust rendering quality based on camera distance ensuring realistic rendering across a wider range of camera orientations than previous approaches. We provide experiments using the ActorsHQ dataset with high-resolution input images. CloseUpAvatar demonstrates both qualitative and quantitative improvements over existing methods in rendering from novel wide range camera positions, while maintaining high FPS by limiting the number of required primitives.

cs.CV↗

arXiv2025

E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework

3D reassembly is a fundamental geometric problem, and in recent years it has increasingly been challenged by deep learning methods rather than classical optimization. While learning approaches have shown promising results, most still rely primarily on geometric features to assemble a whole from its parts. As a result, methods struggle when geometry alone is insufficient or ambiguous, for example, for small, eroded, or symmetric fragments. Additionally, solutions do not impose physical constraints that explicitly prevent overlapping assemblies. To address these limitations, we introduce E-M3RF, an equivariant multimodal 3D reassembly framework that takes as input the point clouds, containing both point positions and colors of fractured fragments, and predicts the transformations required to reassemble them using SE(3) flow matching. Each fragment is represented by both geometric and color features: i) 3D point positions are encoded as rotationconsistent geometric features using a rotation-equivariant encoder, ii) the colors at each 3D point are encoded with a transformer. The two feature sets are then combined to form a multimodal representation. We experimented on four datasets: two synthetic datasets, Breaking Bad and Fantastic Breaks, and two real-world cultural heritage datasets, RePAIR and Presious, demonstrating that E-M3RF on the RePAIR dataset reduces rotation error by 23.1% and translation error by 13.2%, while Chamfer Distance decreases by 18.4% compared to competing methods.

cs.CV↗

arXiv2025

Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions

We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, as current models struggle to obtain coherent image captions due to different camera viewpoints and clutter. We propose a three-phase framework to fine-tune existing captioning models that enhances caption accuracy and consistency across views via a consensus mechanism. First, an agent explores the environment, collecting noisy image-caption pairs. Then, a consistent pseudo-caption for each object instance is distilled via consensus using a large language model. Finally, these pseudo-captions are used to fine-tune an off-the-shelf captioning model, with the addition of contrastive learning. We analyse the performance of the combination of captioning models, exploration policies, pseudo-labeling methods, and fine-tuning strategies, on our manually labeled test set. Results show that a policy can be trained to mine samples with higher disagreement compared to classical baselines. Our pseudo-captioning method, in combination with all policies, has a higher semantic similarity compared to other existing methods, and fine-tuning improves caption accuracy and consistency by a significant margin. Code and test set annotations available at https://hsp-iit.github.io/embodied-captioning/

cs.CV↗

arXiv2025

Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction

Evaluating and comparing the performance of autonomous Humanoid Robots is challenging, as success rate metrics are difficult to reproduce and fail to capture the complexity of robot movement trajectories, critical in Human-Robot Interaction and Collaboration (HRIC). To address these challenges, we propose a general evaluation framework that measures the quality of Imitation Learning (IL) methods by focusing on trajectory performance. We devise the Neural Meta Evaluator (NeME), a deep learning model trained to classify actions from robot joint trajectories. NeME serves as a meta-evaluator to compare the performance of robot control policies, enabling policy evaluation without requiring human involvement in the loop. We validate our framework on ergoCub, a humanoid robot, using teleoperation data and comparing IL methods tailored to the available platform. The experimental results indicate that our method is more aligned with the success rate obtained on the robot than baselines, offering a reproducible, systematic, and insightful means for comparing the performance of multimodal imitation learning approaches in complex HRI tasks.

cs.RO↗

arXiv2025

Sheaves Reloaded: A Directional Awakening

Sheaf Neural Networks (SNNs) represent a powerful generalization of Graph Neural Networks (GNNs) that significantly improve our ability to model complex relational data. While directionality has been shown to substantially boost performance in graph learning tasks and is key to many real-world applications, existing SNNs fall short in representing it. To address this limitation, we introduce the Directed Cellular Sheaf, a special type of cellular sheaf designed to explicitly account for edge orientation. Building on this structure, we define a new sheaf Laplacian, the Directed Sheaf Laplacian, which captures both the graph's topology and its directional information. This operator serves as the backbone of the Directed Sheaf Neural Network (DSNN), the first SNN model to embed a directional bias into its architecture. Extensive experiments on nine real-world benchmarks show that DSNN consistently outperforms baseline methods.

cs.LG↗

arXiv2025

ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction

The task of reassembly is a significant challenge across multiple domains, including archaeology, genomics, and molecular docking, requiring the precise placement and orientation of elements to reconstruct an original structure. In this work, we address key limitations in state-of-the-art Deep Learning methods for reassembly, namely i) scalability; ii) multimodality; and iii) real-world applicability: beyond square or simple geometric shapes, realistic and complex erosion, or other real-world problems. We propose ReassembleNet, a method that reduces complexity by representing each input piece as a set of contour keypoints and learning to select the most informative ones by Graph Neural Networks pooling inspired techniques. ReassembleNet effectively lowers computational complexity while enabling the integration of features from multiple modalities, including both geometric and texture data. Further enhanced through pretraining on a semi-synthetic dataset. We then apply diffusion-based pose estimation to recover the original structure. We improve on prior methods by 57% and 87% for RMSE Rotation and Translation, respectively.

cs.CV↗

arXiv2025

Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding

Graph Neural Networks (GNNs) excel at learning from pairwise interactions but often overlook multi-way and hierarchical relationships. Topological Deep Learning (TDL) addresses this limitation by leveraging combinatorial topological spaces. However, existing TDL models are restricted to undirected settings and fail to capture the higher-order directed patterns prevalent in many complex systems, e.g., brain networks, where such interactions are both abundant and functionally significant. To fill this gap, we introduce Semi-Simplicial Neural Networks (SSNs), a principled class of TDL models that operate on semi-simplicial sets -- combinatorial structures that encode directed higher-order motifs and their directional relationships. To enhance scalability, we propose Routing-SSNs, which dynamically select the most informative relations in a learnable manner. We prove that SSNs are strictly more expressive than standard graph and TDL models. We then introduce a new principled framework for brain dynamics representation learning, grounded in the ability of SSNs to provably recover topological descriptors shown to successfully characterize brain activity. Empirically, SSNs achieve state-of-the-art performance on brain dynamics classification tasks, outperforming the second-best model by up to 27%, and message passing GNNs by up to 50% in accuracy. Our results highlight the potential of principled topological models for learning from structured brain data, establishing a unique real-world case study for TDL. We also test SSNs on standard node classification and edge regression tasks, showing competitive performance. We will make the code and data publicly available.

cs.LG↗

arXiv2025

BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis

We present billboard Splatting (BBSplat) - a novel approach for novel view synthesis based on textured geometric primitives. BBSplat represents the scene as a set of optimizable textured planar primitives with learnable RGB textures and alpha-maps to control their shape. BBSplat primitives can be used in any Gaussian Splatting pipeline as drop-in replacements for Gaussians. The proposed primitives close the rendering quality gap between 2D and 3D Gaussian Splatting (GS), enabling the accurate extraction of 3D mesh as in the 2DGS framework. Additionally, the explicit nature of planar primitives enables the use of the ray-tracing effects in rasterization. Our novel regularization term encourages textures to have a sparser structure, enabling an efficient compression that leads to a reduction in the storage space of the model up to x17 times compared to 3DGS. Our experiments show the efficiency of BBSplat on standard datasets of real indoor and outdoor scenes such as Tanks&Temples, DTU, and Mip-NeRF-360. Namely, we achieve a state-of-the-art PSNR of 29.72 for DTU at Full HD resolution.

cs.CV↗

arXiv2025

AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Critics

This paper presents a framework for generating 3D indoor scenes from text prompts. Existing methods often formulate scene synthesis as an object layout prediction problem conditioned on a single input modality, such as a text description, room shape, or scene graph. This design can lead to object collisions and limited functional plausibility, reducing its practical applicability. To address these limitations, we introduce a multi-stage pipeline that better reflects practical scene creation scenarios. Given a text prompt describing partial scene content, our method first uses graph diffusion to produce a contextually coherent scene graph and then predicts a realistic object layout. In addition, we incorporate lightweight human-object interaction priors to encourage human-centric and functional arrangements, with explicit spatial constraints to reduce interpenetration. Our approach generates coherent 3D scenes with viable layouts that better support human interaction. Experiments on the 3D-FRONT dataset demonstrate that our method achieves competitive or state-of-the-art performance compared with existing approaches, while improving the physical plausibility of generated scenes.

cs.LG↗

arXiv2025

A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation

In image generation, Multiple Latent Variable Generative Models (MLVGMs) employ multiple latent variables to gradually shape the final images, from global characteristics to finer and local details (e.g., StyleGAN, NVAE), emerging as powerful tools for diverse applications. Yet their generative dynamics remain only empirically observed, without a systematic understanding of each latent variable's impact. In this work, we propose a novel framework that quantifies the contribution of each latent variable using Mutual Information (MI) as a metric. Our analysis reveals that current MLVGMs often underutilize some latent variables, and provides actionable insights for their use in downstream applications. With this foundation, we introduce a method for generating synthetic data for Self-Supervised Contrastive Representation Learning (SSCRL). By leveraging the hierarchical and disentangled variables of MLVGMs, our approach produces diverse and semantically meaningful views without the need for real image data. Additionally, we introduce a Continuous Sampling (CS) strategy, where the generator dynamically creates new samples during SSCRL training, greatly increasing data variability. Our comprehensive experiments demonstrate the effectiveness of these contributions, showing that MLVGMs' generated views compete on par with or even surpass views generated from real data. This work establishes a principled approach to understanding and exploiting MLVGMs, advancing both generative modeling and self-supervised learning. Code and pre-trained models at: https://github.com/SerezD/mi_ml_gen.

cs.CV↗

arXiv2024

Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks

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 this study, we propose specific generators, defined Multiple Latent Variable Generative Models (MLVGMs), for adversarial purification. These models possess multiple latent variables that naturally disentangle coarse from fine features. Taking advantage of these properties, we autoencode images to maintain class-relevant information, while discarding and re-sampling any detail, including adversarial noise. The procedure is completely training-free, exploring the generalization abilities of pre-trained MLVGMs on the adversarial purification downstream task. Despite the lack of large models, trained on billions of samples, we show that smaller MLVGMs are already competitive with traditional methods, and can be used as foundation models. Official code released at https://github.com/SerezD/gen_adversarial.

cs.CV↗

arXiv2024

Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving

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 2D and 3D puzzle solving. The fragments and fractures are realistic, caused by a collapse of a fresco during a World War II bombing at the Pompeii archaeological park. The fragments are also eroded and have missing pieces with irregular shapes and different dimensions, challenging further the reassembly algorithms. The dataset is multi-modal providing high resolution images with characteristic pictorial elements, detailed 3D scans of the fragments and meta-data annotated by the archaeologists. Ground truth has been generated through several years of unceasing fieldwork, including the excavation and cleaning of each fragment, followed by manual puzzle solving by archaeologists of a subset of approx. 1000 pieces among the 16000 available. After digitizing all the fragments in 3D, a benchmark was prepared to challenge current reassembly and puzzle-solving methods that often solve more simplistic synthetic scenarios. The tested baselines show that there clearly exists a gap to fill in solving this computationally complex problem.

cs.CV↗

arXiv2024

HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior

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 rendering. We demonstrate its efficiency to animate and render full-body human avatars controlled via the SMPL-X parametric model. Our model learns to apply Gaussian splatting only in areas of the SMPL-X mesh where it is necessary, like hair and out-of-mesh clothing. This results in a minimal number of Gaussians being used to represent the full avatar, and reduced rendering artifacts. This allows us to handle the animation of small body parts such as fingers that are traditionally disregarded. We demonstrate the effectiveness of our approach on two open datasets: SnapshotPeople and X-Humans. Our method demonstrates on par reconstruction quality to the state-of-the-art on SnapshotPeople, while using less than a third of Gaussians. HAHA outperforms previous state-of-the-art on novel poses from X-Humans both quantitatively and qualitatively.

cs.CV↗

arXiv2024

DLGNet: Hyperedge Classification through Directed Line Graphs for Chemical Reactions

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, they are rapidly expanding in domains such as chemistry and biology, especially in the areas of drug discovery and molecule generation. One of the areas witnessing the fasted growth is the chemical reactions field, where chemical reactions can be naturally encoded as directed hyperedges of a hypergraph. In this paper, we address the chemical reaction classification problem by introducing the notation of a Directed Line Graph (DGL) associated with a given directed hypergraph. On top of it, we build the Directed Line Graph Network (DLGNet), the first spectral-based Graph Neural Network (GNN) expressly designed to operate on a hypergraph via its DLG transformation. The foundation of DLGNet is a novel Hermitian matrix, the Directed Line Graph Laplacian, which compactly encodes the directionality of the interactions taking place within the directed hyperedges of the hypergraph thanks to the DLG representation. The Directed Line Graph Laplacian enjoys many desirable properties, including admitting an eigenvalue decomposition and being positive semidefinite, which make it well-suited for its adoption within a spectral-based GNN. Through extensive experiments on chemical reaction datasets, we show that DGLNet significantly outperforms the existing approaches, achieving on a collection of real-world datasets an average relative-percentage-difference improvement of 33.01%, with a maximum improvement of 37.71%.

cs.LG↗

arXiv2024

Model Debiasing by Learnable Data Augmentation

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 models are often prone to learn spurious correlations between data and labels. In this work, we tackle the problem of learning from biased data in the very realistic unsupervised scenario, i.e., when the bias is unknown. This is a much harder task as compared to the supervised case, where auxiliary, bias-related annotations, can be exploited in the learning process. This paper proposes a novel 2-stage learning pipeline featuring a data augmentation strategy able to regularize the training. First, biased/unbiased samples are identified by training over-biased models. Second, such subdivision (typically noisy) is exploited within a data augmentation framework, properly combining the original samples while learning mixing parameters, which has a regularization effect. Experiments on synthetic and realistic biased datasets show state-of-the-art classification accuracy, outperforming competing methods, ultimately proving robust performance on both biased and unbiased examples. Notably, being our training method totally agnostic to the level of bias, it also positively affects performance for any, even apparently unbiased, dataset, thus improving the model generalization regardless of the level of bias (or its absence) in the data.

cs.LG↗

arXiv2024

Look Around and Learn: Self-Training Object Detection by Exploration

When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e., a fully self-supervised approach. In our setting, an agent initially learns to explore the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we learn the exploration policy Look Around to mine hard samples, and we devise a novel mechanism called Disagreement Reconciliation for producing refined pseudo-labels from the consensus among observations. We implement a unified benchmark of the current state-of-the-art and compare our approach with pre-existing exploration policies and perception mechanisms. Our method is shown to outperform existing approaches, improving the object detector by 6.2% in a simulated scenario, a 3.59% advancement over other state-of-the-art methods, and by 9.97% in the real robotic test without relying on ground-truth. Code for the proposed approach and baselines are available at https://iit-pavis.github.io/Look_Around_And_Learn/.

cs.CV↗

arXiv2024

XBG: End-to-end Imitation Learning for Autonomous Behaviour in Human-Robot Interaction and Collaboration

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 paper is an architecture for learning HRI behaviours using a data-driven approach. Through teleoperation, a diverse dataset is collected, comprising demonstrations across multiple HRI scenarios, including handshaking, handwaving, payload reception, walking, and walking with a payload. After synchronizing, filtering, and transforming the data, different Deep Neural Networks (DNN) models are trained. The final system integrates different modalities comprising exteroceptive and proprioceptive sources of information to provide the robot with an understanding of its environment and its own actions. The robot takes sequence of images (RGB and depth) and joints state information during the interactions and then reacts accordingly, demonstrating learned behaviours. By fusing multimodal signals in time, we encode new autonomous capabilities into the robotic platform, allowing the understanding of context changes over time. The models are deployed on ergoCub, a real-world humanoid robot, and their performance is measured by calculating the success rate of the robot's behaviour under the mentioned scenarios.

cs.RO↗