Elisabetta Fedele

I am a Computer Science PhD student at ETH Zürich, working on 3D Computer Vision and Machine Learning, under the supervision of Prof. Marc Pollefeys and Prof. Bernhard Schölkopf. I am also a Doctoral Fellow at the ETH AI Center.
Previously, I was a Computer Science Master's student at ETH Zürich, focusing in Theoretical Computer Science and Machine Learning, with a particular focus on its application in the field of Computer Vision.
During my Master I have been working on Open-Vocabulary 3D scene understanding, Diffusion Models for image generation, and primitive-based 3D scene reconstruction.
I was also interested in topics from Theoretical Computer Science and in 2023 I have spent the summer doing a Research Internship at EPFL, in Alessandro Chiesa's lab.

Email / Twitter / CV / Google Scholar / Linkedin / Github

News

March 2025: I started my Research Visit in Guibas Lab in Stanford. I will be here for the next 6 months!
September 2024: I started my PhD in Computer Vision at ETH Zürich and I joined ETH AI Center as a Doctoral Fellow!
August 2024: Our work FABRIC was accepted at the FOCUS Workshop at ECCV 2024 in Milan!
July 2024: I defended my Master's thesis and I have received the MSc in Computer Science from ETH Zürich!
July 2024: I attended ICVSS 2024 in Sicily and our poster for OpenMask3D won 3rd place for the Best Poster Awards!
May 2024: Our work Blendy was presented at ZKProof6 2024 in Berlin!
September 2023: Our work OpenMask3D was accepted at NeurIPS 2023 in New Orleans!

Selected Research

SuperDec: 3D Scene Decomposition with Superquadric Primitives
Elisabetta Fedele, Boyang Sun, Leonidas Guibas, Marc Pollefeys, Francis Engelmann
arXiv 2025
project page / arXiv

SuperDec allows to represent arbitrary 3D scenes with a compact and modular set of superquadric primitives.

FABRIC: Personalizing Diffusion Models with Iterative Feedback
Dimitri Von Rütte*, Elisabetta Fedele*, Jonathan Thomm*, Lukas Wolf*
ECCVW 2024
project page / arXiv / code

FABRIC is a training-free approach that conditions the diffusion process on a set of feedback images, applicable to a wide range of popular diffusion models.

OpenMask3D: Open-Vocabulary 3D Instance Segmentation
Ayça Takmaz*, Elisabetta Fedele*, Robert W. Sumner, Marc Pollefeys, Federico Tombari,
Francis Engelmann
NeurIPS 2023
project page / arXiv / code

OpenMask3D is a zero-shot approach to perform 3D Instance Segmentation with Open-Vocabulary queries.

Others

A Time-Space Tradeoff for the Sumcheck Prover
Alessandro Chiesa*, Elisabetta Fedele*, Giacomo Fenzi*, Andrew Zitek-Estrada*
ZKProof Workshop 6, Berlin 2024
blog post / ePrint / code

Blendy is a new concretely efficient algorithm for multilinear sumcheck proving which uses linear time and sublinear memory.