FUSE: A Flow-based Mapping Between Shapes
Lorenzo Olearo, Giulio Viganò, Daniele Baieri, Filippo Maggioli, Simone Melzi. FUSE: A Flow-based Mapping Between Shapes. ECCV 2026.
Resume
Education
- Ph.D. in Computer Science, Sapienza University of Rome, 2025 (Advisor: Prof. Emanuele Rodolà)
- M.Sc. in Computer Science, Sapienza University of Rome, 2021
- B.Sc. in Computer Science, Sapienza University of Rome, 2019
Academic Appointments
- 2026/2027: Humboldt PostDoc Fellow
- University of Bonn, Institut für Informatik
- Project: LENS: Rethinking Geometric Deep Learning via Local Embeddings for Neural Surfaces
- Research Group: Geometry in Machine Learning (Prof. Zorah Lähner)
- Spring 2026: Visiting PostDoc
- University of Bonn, Institut für Informatik
- Funded by Lamarr Institute
- Research Group: Geometry in Machine Learning (Prof. Zorah Lähner)
- 2025/2026: PostDoc Researcher
- University of Milano-Bicocca, DISCo
- Research activity on cross-representation shape matching and local geometry representations
- Tutored the department’s Foundations of Game Design course
- Research Group: 3DiG (Prof. Simone Melzi)
- November 2023: Visiting Ph.D. student
- University of Siegen, Institute for Vision and Graphics
- Research Group: Computer Vision Group (Prof. Michael Möller)
Grants
- Humboldt PostDoc Fellowship
- Salary grant for a research stay of 1 year at the University of Bonn
- Project: LENS: Rethinking Geometric Deep Learning via Local Embeddings for Neural Surfaces
- Lamarr Stipendium
- Funding living expenses for a research visit of 3 months at the University of Bonn
- Total funding: 11000€
- Sapienza University Research Starting Grant
- Internal grant for Ph.D. students, funding travel and equipment
- Total funding: 1332€
Awards
- CVPR 2026 Outstanding Reviewer
- MSCA 2025 Seal of Excellence (PostDoctoral Fellowships)
- ECCV 2024 Outstanding Reviewer
- Sapienza University Excellent Graduate A.Y. 2020/21
Publications
Model-based Metric 3D Shape and Motion Reconstruction of Wild Bottlenose Dolphins in Drone-Shot Videos
Daniele Baieri, Riccardo Cicciarella, Michael Krützen, Emanuele Rodolà and Silvia Zuffi. Model-based metric 3D shape and motion reconstruction of wild bottlenose dolphins in drone-shot videos. Int J Comput Vis 134, 293 (2026). https://doi.org/10.1007/s11263-026-02906-z
Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
Daniele Baieri, Filippo Maggioli, Emanuele Rodolà, Simone Melzi and Zorah Lähner. Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing. In Advances in Neural Information Processing Systems, 2026
\(C^2M^3\): Cycle-Consistent Multi-Model Merging
Donato Crisostomi, Marco Fumero, Daniele Baieri, Florian Bernard, and Emanuele Rodolà. $C^2M^3$: Cycle-consistent multi-model merging. In Advances in Neural Information Processing Systems, 2025
Rematching: Low-Resolution Representations for Scalable Shape Correspondence
Filippo Maggioli, Daniele Baieri, Emanuele Rodolà, Simone Melzi. ReMatching: Low-Resolution Representations for Scalable Shape Correspondence. ECCV 2024. Lecture Notes in Computer Science, vol 15095.
GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splatting
Francesco Palandra, Andrea Sanchietti, Daniele Baieri, and Emanuele Rodolà. Gsedit: Efficient text-guided editing of 3d objects via gaussian splatting. arXiv preprint. arXiv:2403.05154, 2024
Newton’s Fractals on Surfaces via Bicomplex Algebra
Filippo Maggioli, Daniele Baieri, Simone Melzi, and Emanuele Rodolà. 2022. Newton’s Fractals on Surfaces via Bicomplex Algebra. In ACM SIGGRAPH 2022 Posters (SIGGRAPH '22). Association for Computing Machinery, New York, NY, USA, Article 65, 1–2
Talks
Patch-based Methods in Data-Driven Geometry Processing
Talk at Politecnico di Milano, Department of Electronics, Information and Bioengineering, Milan, Italy
Practical 3D Graphics: Performance Enhancement in CG Pipelines
Talk at University of Siegen, Department of Computer Science, Siegen, Germany
Teaching
Service and leadership
- Reviewing for top-tier Computer Vision and Artificial Intelligence conferences:
- NeurIPS, CVPR, ECCV, ICCV
- Reviewing for high-impact venues in Computer Graphics:
- Computer Graphics Forum, Computers and Graphics, Symposium on Geometry Processing