Lorenzo Stacchio
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lorenzo Stacchio has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Emanuele Frontoni
Department of Political Sciences, Communication and International Relations, University of Macerata, Macerata, Italy
9 shared publications - Gustavo Marfia
University of Bologna, Bologna, Italy
7 shared publications - Marina Paolanti
Department of Political Sciences, Communication and International Relations, University of Macerata, 62100 Macerata, Italy
7 shared publications - Emanuele Balloni
Università Politecnica delle Marche
5 shared publications - Primo Zingaretti
Università Politecnica delle Marche
5 shared publications - Roberto Pierdicca
Department of Civil and Building Engineering and Architecture (DICEA), Università Politecnica delle Marche, 60131 Ancona, Italy
4 shared publications
Latest Publications
- Open Access
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 7219-7230
Orchestrating Generative AI Paradigms With Human-in-the-Loop for 3D Generation
Generative AI techniques are revolutionizing the creation of 3D and immersive content, yet challenges remain, such as achieving precise user control in 3D generation. Current text-to-3D and image-to-3D pipelines often produce outputs that deviate from user expectations, lacking the ability to refine or correct generated models effectively. To address these limitations, we propose Imagin3D, a novel human-in-the-loop (HITL) system that integrates Multimodal Large Language Models to enhance the controllability and adaptability of 3D content generation. Imagin3D leverages a Multi-View Question Answering module to evaluate the consistency of generated views with user-provided textual descriptions, enabling iterative refinement through guided inpainting while preserving multi-view consistency. This allows users to co-create 3D models, which are then synthesized into a final 3D asset using Neural Rendering. We validate Imagin3D through extensive quantitative evaluations and a comprehensive user study, demonstrating its effectiveness in improving usability, accuracy, and user satisfaction in interactive 3D generation tasks. Our results highlight the potential of HITL approaches to bridge the gap between AI-generated outputs and user intent, paving the way for more accessible and user-centered 3D generation workflows.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 7219-7230
Open AccessOrchestrating Generative AI Paradigms With Human-in-the-Loop for 3D Generation
Generative AI techniques are revolutionizing the creation of 3D and immersive content, yet challenges remain, such as achieving precise user control in 3D generation. Current text-to-3D and image-to-3D pipelines often produce outputs that deviate from user expectations, lacking the ability to refine or correct generated models effectively. To address these limitations, we propose Imagin3D, a novel human-in-the-loop (HITL) system that integrates Multimodal Large Language Models to enhance the controllability and adaptability of 3D content generation. Imagin3D leverages a Multi-View Question Answering module to evaluate the consistency of generated views with user-provided textual descriptions, enabling iterative refinement through guided inpainting while preserving multi-view consistency. This allows users to co-create 3D models, which are then synthesized into a final 3D asset using Neural Rendering. We validate Imagin3D through extensive quantitative evaluations and a comprehensive user study, demonstrating its effectiveness in improving usability, accuracy, and user satisfaction in interactive 3D generation tasks. Our results highlight the potential of HITL approaches to bridge the gap between AI-generated outputs and user intent, paving the way for more accessible and user-centered 3D generation workflows.
- Open Access
- 24 June 2026
- Published by Springer Nature in Virtual Reality
- Vol. 30 (4)
Xarnold: assessing the role of virtual humans in immersive fitness environments with aligned flat, multi-view, and 3D parametric visual instruction guidance
Recent advances in Extended Reality (XR) allow the creation of immersive fitness and virtual coaching systems. However, it remains unclear whether immersive visualization modalities influence users’ perception, understanding, and confidence in performing exercises. Moreover, it is unclear whether this improves those with respect to a classical 2D visualization. In this work, we investigate the role of a parametric 3D human model in enhancing workout perception and social presence within immersive fitness environments. To this date, we have designed a modular XR system, named XaRNold , that allows the visualization of single/multi-view video, and a parametric 3D model called Skinned Multi-Person Linear Model (SMPL) showing how to perform a physical exercise. We conducted a controlled user study (N=30) to compare participants’ cognitive load, understanding, technology acceptance, usability, and social perceptions and engagement across visualization modes. We employ the Fit3D dataset, which provides aligned 2D, multi-view, and related 3D poses data for diverse physical exercises. The results indicate that a parametric virtual human model provides a favorable trade-off between the measured constructs, offering a clearer understanding of why and how avatar-based guidance can be used and paving the way for more effective and empathic virtual fitness systems.
- 24 June 2026
- Published by Springer Nature in Virtual Reality
- Vol. 30 (4)
Open AccessXarnold: assessing the role of virtual humans in immersive fitness environments with aligned flat, multi-view, and 3D parametric visual instruction guidance
Recent advances in Extended Reality (XR) allow the creation of immersive fitness and virtual coaching systems. However, it remains unclear whether immersive visualization modalities influence users’ perception, understanding, and confidence in performing exercises. Moreover, it is unclear whether this improves those with respect to a classical 2D visualization. In this work, we investigate the role of a parametric 3D human model in enhancing workout perception and social presence within immersive fitness environments. To this date, we have designed a modular XR system, named XaRNold , that allows the visualization of single/multi-view video, and a parametric 3D model called Skinned Multi-Person Linear Model (SMPL) showing how to perform a physical exercise. We conducted a controlled user study (N=30) to compare participants’ cognitive load, understanding, technology acceptance, usability, and social perceptions and engagement across visualization modes. We employ the Fit3D dataset, which provides aligned 2D, multi-view, and related 3D poses data for diverse physical exercises. The results indicate that a parametric virtual human model provides a favorable trade-off between the measured constructs, offering a clearer understanding of why and how avatar-based guidance can be used and paving the way for more effective and empathic virtual fitness systems.
- 2 January 2026
- Published by Springer Nature
- p. 649-660
A Modular and Efficient Framework for the Development of Large Language Model-Based Virtual Humans: An Educational Scenario
- 2 January 2026
- Published by Springer Nature
- p. 649-660
A Modular and Efficient Framework for the Development of Large Language Model-Based Virtual Humans: An Educational Scenario
- 2 January 2026
- Published by Springer Nature
- p. 376-388
Ego and Exo Views for an Object-Level Human Behavior Analysis and Understanding Through Tracking in Retail Spaces
- 2 January 2026
- Published by Springer Nature
- p. 376-388
Ego and Exo Views for an Object-Level Human Behavior Analysis and Understanding Through Tracking in Retail Spaces
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 2305-2309
RELD: Regularization by Latent Denoising
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 2305-2309
RELD: Regularization by Latent Denoising
- Open Access
Empathic Prompting: Non-Verbal Context Integration for Multimodal LLM Conversations
We present Empathic Prompting, a novel framework for multimodal human-AI interaction that enriches Large Language Model (LLM) conversations with implicit non-verbal context. The system integrates a commercial facial expression recognition service to capture users' emotional cues and embeds them as contextual signals during prompting. Unlike traditional multimodal interfaces, empathic prompting requires no explicit user control; instead, it unobtrusively augments textual input with affective information for conversational and smoothness alignment. The architecture is modular and scalable, allowing integration of additional non-verbal modules. We describe the system design, implemented through a locally deployed DeepSeek instance, and report a preliminary service and usability evaluation (N=5). Results show consistent integration of non-verbal input into coherent LLM outputs, with participants highlighting conversational fluidity. Beyond this proof of concept, empathic prompting points to applications in chatbot-mediated communication, particularly in domains like healthcare or education, where users' emotional signals are critical yet often opaque in verbal exchanges.
Open AccessEmpathic Prompting: Non-Verbal Context Integration for Multimodal LLM Conversations
We present Empathic Prompting, a novel framework for multimodal human-AI interaction that enriches Large Language Model (LLM) conversations with implicit non-verbal context. The system integrates a commercial facial expression recognition service to capture users' emotional cues and embeds them as contextual signals during prompting. Unlike traditional multimodal interfaces, empathic prompting requires no explicit user control; instead, it unobtrusively augments textual input with affective information for conversational and smoothness alignment. The architecture is modular and scalable, allowing integration of additional non-verbal modules. We describe the system design, implemented through a locally deployed DeepSeek instance, and report a preliminary service and usability evaluation (N=5). Results show consistent integration of non-verbal input into coherent LLM outputs, with participants highlighting conversational fluidity. Beyond this proof of concept, empathic prompting points to applications in chatbot-mediated communication, particularly in domains like healthcare or education, where users' emotional signals are critical yet often opaque in verbal exchanges.
- 12 May 2025
- Published by Springer Nature
- p. 352-367
Deep Armocromia: A Novel Dataset for Face Seasonal Color Analysis and Classification
- 12 May 2025
- Published by Springer Nature
- p. 352-367
Deep Armocromia: A Novel Dataset for Face Seasonal Color Analysis and Classification
- 12 May 2025
- Published by Springer Nature
- p. 312-329
A Data-Centric Module for Neural Rendering
- 22 April 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 153
A Neural Rendering system for fashion design process
- 22 April 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 153
A Neural Rendering system for fashion design process
- Open Access
RELD: Regularization by Latent Diffusion Models for Image Restoration
In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle, we introduce an approach that integrates a Latent Diffusion Model, trained for the denoising task, into a variational framework using Half-Quadratic Splitting, exploiting its regularization properties. This approach, under appropriate conditions that can be easily met in various imaging applications, allows for reduced computational cost while achieving high-quality results. The proposed strategy, called Regularization by Latent Denoising (RELD), is then tested on a dataset of natural images, for image denoising, deblurring, and super-resolution tasks. The numerical experiments show that RELD is competitive with other state-of-the-art methods, particularly achieving remarkable results when evaluated using perceptual quality metrics.
Open AccessRELD: Regularization by Latent Diffusion Models for Image Restoration
In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle, we introduce an approach that integrates a Latent Diffusion Model, trained for the denoising task, into a variational framework using Half-Quadratic Splitting, exploiting its regularization properties. This approach, under appropriate conditions that can be easily met in various imaging applications, allows for reduced computational cost while achieving high-quality results. The proposed strategy, called Regularization by Latent Denoising (RELD), is then tested on a dataset of natural images, for image denoising, deblurring, and super-resolution tasks. The numerical experiments show that RELD is competitive with other state-of-the-art methods, particularly achieving remarkable results when evaluated using perceptual quality metrics.