Luigi Piccinelli

Luigi Piccinelli

PhD student in Computer Vision

ETH Zurich

Biography

I’m a Ph.D. student at the Computer Vision LAb of ETH Zürich working with Prof. Luc Van Gool. I obtained my B.Sc. and M.Sc. degrees in Electrical Engineering from University of Bologna and ETH Zurich, respectively, where I worked with Dr. Christos Skarardis as a student research assistant in Computer Vision. My research focuses on 3D perception from both images and videos.

Interests
  • Computer Vision
  • 3D Perception
  • Artificial Intelligence
Education

  • PhD in Computer Vision, 2022 - now

    ETH Zurich

  • MSc in Electrical Engineering, 2019 - 2022

    ETH Zurich

  • BSc in Automation Engineering, 2016 - 2019

    University of Bologna

Selected Publications

UniDepth: Universal Monocular Metric Depth Estimation
UniDepth is capable of reconstructing metric 3D scenes from solely single images across domains. UniDepth directly predicts metric 3D points from the input image at inference time without any additional information.
Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segu, Siyuan Li, Luc Van Gool, Fisher Yu
(Highlight) Conference on Computer Vision and Pattern Recognition (CVPR), 2024
ArXiv PDF Code Cite Video
UniDepth: Universal Monocular Metric Depth Estimation
iDisc: Internal Discretization for Monocular Depth Estimation
iDisc learns scene-level patterns via the proposed internal discretized representations. The method implicitly partitions the scene into a set of high-level patterns.
Luigi Piccinelli, Christos Sakaridis, Fisher Yu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
ArXiv PDF Code Cite Video
iDisc: Internal Discretization for Monocular Depth Estimation

Experience

 
 
 
 
 
Computer Vision Research Intern
ETH Zurich
May 2022 – December 2022 Zurich, CH
Monocular Depth Estimation.
 
 
 
 
 
Computer Vision Research Intern
IBM Inc.
September 2021 – April 2022 Zurich, CH
Domain Incremental Learning for gigapixel images.
 
 
 
 
 
Computer Vision Intern
Second Spectrun Inc.
March 2021 – September 2021 Lausanne, CH
Image-to-image transfer from synthetic images to real-human appearance.
 
 
 
 
 
Electrical Engineer Intern
IBD s.r.l
March 2019 – June 2019 Bologna, IT
Design of non-invasive blood concentration sensor.

Contact