AI & Graphics Researcher

AI & Graphics Researcher

PostDoc & Freelance 3D Tech Artist.

Posts by Collection

portfolio

publications

Moving Drones for Wireless Coverage in a Three-Dimensional Grid Analyzed via Game Theory

Published in 2021 IEEE Asia Pacific Conference on on Circuits and Systems (APCCAS), 1900

This paper analyzes the movement of drones for wireless coverage in a 3D grid using game theory.

Recommended citation: Camuffo, E., Gorghetto, L., & Badia, L. (2021). "Moving Drones for Wireless Coverage in a Three-Dimensional Grid Analyzed via Game Theory." In Proceedings of the 2021 IEEE Asia Pacific Conference on on Circuits and Systems (APCCAS).
Download Paper | Download Slides

3D Model Optimization for Immersive and Interactive Applications

Published in European Workshop on Visual Information Processing (EUVIP), 1900

Questo articolo presenta strategie per ottimizzare modelli 3D profondi al fine di migliorare le prestazioni in applicazioni immersive e interattive.

Recommended citation: Camuffo, E., Battisti, F., Pham, F., & Milani, S. (2022). "3D Model Optimization for Immersive and Interactive Applications." European Workshop on Visual Information Processing (EUVIP).
Download Paper | Download Slides

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine Strategies on Sparse Data

Published in International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1900

This study explores continual learning approaches for LiDAR semantic segmentation, focusing on class-incremental and coarse-to-fine strategies to manage sparse data.

Recommended citation: Camuffo, E., & Milani, S. (2023). "Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine Strategies on Sparse Data." International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Download Paper

FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images

Published in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1900

This paper proposes an FFT-based method to select and optimize statistical features, enhancing the recognition of images with severe corruptions.

Recommended citation: Camuffo, E., Michieli, U., Moon, J. J., Kim, D., & Ozay, M. (2023). "FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images." International Conference on Acoustics, Speech, and Signal Processing (ICASSP).
Download Paper

Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation

Published in Transactions on Multimedia (TMM), 1900

This study introduces a self-regularizing approach for point cloud semantic segmentation, enabling the model to learn from mistakes and improve hierarchical representations.

Recommended citation: Camuffo, E., Michieli, U., & Milani, S. (2023). "Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation." Transactions on Multimedia (TMM), 25(1), 567-578.
Download Paper

Fully Automated Scan-to-BIM via Point Cloud Instance Segmentation

Published in International Conference on Image Processing (ICIP), 1900

This research introduces a fully automated method for Scan-to-BIM processes using point cloud instance segmentation to enhance building information modeling.

Recommended citation: Campagnolo, D., Camuffo, E., Michieli, U., Borin, P., Milani, S., & Giordano, A. (2023). "Fully Automated Scan-to-BIM via Point Cloud Instance Segmentation." International Conference on Image Processing (ICIP).
Download Paper | Download Slides

Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network

Published in International Conference on Image Processing (ICIP), 1900

This work presents a multi-modal network for continual semantic segmentation of road scenes, aligning features symmetrically to handle new data effectively.

Recommended citation: Barbato, F., Camuffo, E., Milani, S., & Zanuttigh, P. (2024). "Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network." International Conference on Image Processing (ICIP).
Download Paper

Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics

Published in International Conference on Intelligent Robots and Systems (IROS), 1900

This paper introduces a method to improve model robustness against input corruptions by adapting normalization statistics for each specific corruption type.

Recommended citation: Camuffo, E., Michieli, U., Milani, S., Moon, J. J., & Ozay, M. (2024). "Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics." International Conference on Intelligent Robots and Systems (IROS).
Download Paper

Age of Information for Quantum Communication Channels with Monogamy of Entanglement

Published in International Mediterranean Conference on Communications and Networking (MeditCOM), 1900

Recommended citation: Jabrayilova A., Camuffo E., Crosara L., & Badia L., "Age of Information for Quantum Communication Channels with Monogamy of Entanglement", International Mediterranean Conference on Communications and Networking (MeditCOM), 2025.

Claycode: Stylable and Deformable 2D Scannable Codes

Published in Transactions on Graphics (TOG), 1900

This paper proposes a novel 2D scannable code with improved personalizability.

Recommended citation: Maida M., Crescini A., Perronet M, & Camuffo E., "Claycode: Stylable and Deformable 2D Scannable Codes", Transactions on Graphics (TOG), 2025. [Oral presentation at SIGGRAPH 2025, video selected for CAF Teaser].
Download Paper

SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality

Published in European Signal Processing Conference (EUSIPCO), 1900

A novel approach leveraging semantic-driven techniques to enhance Gaussian splatting for immersive extended reality applications.

Recommended citation: Schiavo C., Camuffo E., Badia L., & Milani S., "SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality", European Signal Processing Conference (EUSIPCO), 2025.
Download Paper

teaching

3D Vision and Extended Reality

Undergraduate course, M.Sc. in Internet and Multimedia Engineering, University of Padova, 1900

This course (taught 2019–2024) provided an introduction to the principles of 3D vision and extended reality (XR), emphasizing practical applications and development using Unity3D. Key topics included 3D reconstruction, virtual environments, interaction techniques and machine learning.
GitHub repository.

Other Teaching Experiences

Undergraduate courses, M.Sc. in Internet and Multimedia Engineering, University of Padova, 2021

  • Digital Forensis (2019–2020): Explored the intersection of digital tools and forensic analysis.
  • Immersive and Interactive Multimedia (2020–2021): Focused on creating engaging multimedia experiences.
  • Usability and User Experience (2020–2021): Covered principles and practices for designing user-friendly systems.

High School Activity

PCTO Program, Various High Schools, 2023

This course was led in high school to introduce the fundamentals of machine learning and computer vision through an engaging mix of theory, hands-on coding, and interactive examples. Delivered as part of a science outreach initiative, it is designed to make AI concepts accessible, fun, and visually intuitive.