Publications

2026

1. Unraveling Brainstem Deformations in Joubert Syndrome: A Statistical Shape Analysis of MRI-Derived Structures

   Francesca Maccarone, Giorgio Longari, Filippo Arrigoni, and 2 more authors

   In Medical Image Computing and Computer Assisted Intervention – MICCAI 2025, 2026

   Abs

   Statistical shape analysis (SSA) is a powerful tool for studying anatomical structures and their geometric variations in medical imaging. In this work, we analyze real MRI-derived data to explore correlations between geometric deformations and Joubert syndrome (JS). Building on prior SSA research, we tailor the preprocessing pipeline to an in-house dataset and perform a detailed shape variability analysis using principal component analysis (PCA). A random forest classifier is then applied, achieving high classification accuracy. To ensure robustness, we test multiple train-test splits and evaluate their impact. In addition, we support clinical interpretation by providing visualizations that combine 3D and 2D information, resembling typical diagnostic paradigms on MRI planes. Our work offers some methodological insights into shape-based analysis and aims to serve as a practical tool for the medical community. Code and data are openly available at: https://github.com/Franca-exe/SSA-brainstem.

2025

1. Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing

   Daniele Baieri, Filippo Maggioli, Emanuele Rodolà, and 2 more authors

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
2. SIGGRAPH

   

   NAM: Neural Adjoint Maps for refining shape correspondences

   Giulio Viganò, Maks Ovsjanikov, and Simone Melzi

   Transactions On Graphics, 2025

   DOI
3. Preprint

   

   Blending Concepts with Text-to-Image Diffusion Models

   Lorenzo Olearo, Giorgio Longari, Alessandro Raganato, and 2 more authors

   2025

   Abs HTML PDF

   Diffusion models have dramatically advanced text-to-image generation in recent years, translating abstract concepts into high-fidelity images with remarkable ease. In this work, we examine whether they can also blend distinct concepts, ranging from concrete objects to intangible ideas, into coherent new visual entities under a zero-shot framework. Specifically, concept blending merges the key attributes of multiple concepts (expressed as textual prompts) into a single, novel image that captures the essence of each concept. We investigate four blending methods, each exploiting different aspects of the diffusion pipeline (e.g., prompt scheduling, embedding interpolation, or layer-wise conditioning). Through systematic experimentation across diverse concept categories, such as merging concrete concepts, synthesizing compound words, transferring artistic styles, and blending architectural landmarks, we show that modern diffusion models indeed exhibit creative blending capabilities without further training or fine-tuning. Our extensive user study, involving 100 participants , reveals that no single approach dominates in all scenarios: each blending technique excels under certain conditions, with factors like prompt ordering, conceptual distance, and random seed affecting the outcome. These findings highlight the remarkable compositional potential of diffusion models while exposing their sensitivity to seemingly minor input variations.

4. Escaping Plato’s Cave: Towards the Alignment of 3D and Text Latent Spaces

   Souhail Hadgi, Luca Moschella, Andrea Santilli, and 5 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

   DOI
5. ReMatching: Low-Resolution Representations for Scalable Shape Correspondence

   Filippo Maggioli, Daniele Baieri, Emanuele Rodolà, and 1 more author

   In Computer Vision – ECCV 2024, Jun 2025

   Abs

   We introduce ReMatching, a novel shape correspondence solution based on the functional maps framework. Our method, by exploiting a new and appropriate re-meshing paradigm, can target shape-matching tasks even on meshes counting millions of vertices, where the original functional maps does not apply or requires a massive computational cost. The core of our procedure is a time-efficient remeshing algorithm which constructs a low-resolution geometry while acting conservatively on the original topology and metric. These properties allow translating the functional maps optimization problem on the resulting low-resolution representation, thus enabling efficient computation of correspondences with functional map approaches. Finally, we propose an efficient technique for extending the estimated correspondence to the original meshes. We show that our method is more efficient and effective through quantitative and qualitative comparisons, outperforming state-of-the-art pipelines in quality and computational cost.

2024

1. S4A: Scalable Spectral Statistical Shape Analysis

   Francesca Maccarone, Giorgio Longari, Giulio Viganò, and 3 more authors

   In Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference, Jun 2024

   DOI
2. Bijective upsampling and learned embedding for point clouds correspondences

   Giulio Viganò and Simone Melzi

   Computers and Graphics, Jun 2024

   DOI
3. KGM @ ECCV

   

   How to Blend Concepts in Diffusion Models

   Lorenzo Olearo, Giorgio Longari, Simone Melzi, and 2 more authors

   arXiv preprint arXiv:2407.14280, Jun 2024

   Abs HTML PDF

   For the last decade, there has been a push to use multi-dimensional (latent) spaces to represent concepts; and yet how to manipulate these concepts or reason with them remains largely unclear. Some recent methods exploit multiple latent representations and their connection, making this research question even more entangled. Our goal is to understand how operations in the latent space affect the underlying concepts. To that end, we explore the task of concept blending through diffusion models. Diffusion models are based on a connection between a latent representation of textual prompts and a latent space that enables image reconstruction and generation. This task allows us to try different text-based combination strategies, and evaluate easily through a visual analysis. Our conclusion is that concept blending through space manipulation is possible, although the best strategy depends on the context of the blend.

4. STAG

   

   Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence

   Alessandro Riva, Alessandro Raganato, and Simone Melzi

   In Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference, Jun 2024

   DOI