About Me

I am a Machine Learning researcher currently working at XXII

Before working at XXII, I was working at Upstride, which got acquired by ContentSquare. Before that, I was working at ENSTA Paris. There I was a PhD student from 2016 to 2019, and from 2019 to 2021 I was a postdoc researcher. During my PhD, I was advised by Antoine Manzanera, David Filliat and Laure Chevalley (at Parrot).

My research interest focuses mostly on 3D computer vision and geometry.

You can download my PhD thesis here: Robust Learning of a depth map for obstacle avoidance with a monocular stabilized flying camera

Published works

Talk, Meetup Compter vision Paris
Clément Pinard

Lours, the Pandas companion

Project / Github / Slides
Article
Clément Pinard and Antoine Manzanera

Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the masses

Project / Paper / ArXiV / Hal / Springer / Bib
Talk, Human Talk Paris
Clément Pinard

On the usefulness of imperfect models : Mercator's redemption

Project / Talk (in French)
Blog Post, Contensquare Engineering blog
Clément Pinard

A review of SageDB, the Self-Assembling Database System

BlogPost
Conference Paper, ICRA
Varun Ravi Kumar, Sandesh Athni Hiremath, Markus Bach, Christian Witt, Clément Pinard, Senthil Yogamani and Patrick Maeder

Fisheyedistancenet: Self-supervised scale-aware distance estimation using monocular fisheye camera for autonomous driving

Project / Video / Paper / ArXiV / Bib
Phd Thesis
Clément Pinard

Robust Learning of a depth map for obstacle avoidance with a monocular stabilized flying camera

Project / Manuscript / Defense / Hal / Bib
Workshop Paper, GDML Workshop at ECCV18
Clément Pinard, Antoine Manzanera, David Filliat and Laure Chevalley

Learning Structure From Motion From Motion

Project / Paper / Poster / ArXiV / Hal / Bib
Conference Paper, ECMR
Clément Pinard, Antoine Manzanera, David Filliat and Laure Chevalley

Multi range Real-time depth inference from a monocular stabilized footage using a Fully Convolutional Neural Network

Project / Paper / Poster / ArXiV / Hal / Bib
Conference Paper, UAV-g
Clément Pinard, Antoine Manzanera, David Filliat and Laure Chevalley

End-to-end depth from motion with stabilized monocular videos

Project / Paper / Presentation / ArXiV / Hal / Bib