tom_monnier.jpg

Tom Monnier

PhD candidate at Imagine - ENPC

6-8 Av Blaise Pascal - Cité Descartes
77455 Marne-la-Vallée, France

Email: tom dot monnier at enpc dot fr

I am a third-year PhD candidate (exp. graduation on 05/2023) in the Imagine research group at École des Ponts ParisTech (ENPC) under the supervision of Mathieu Aubry. Before that, I received my engineering degree in mathematics and computer science from Mines ParisTech.

I am interested in machine learning, computer vision and graphics. My research currently focuses on finding ways to solve computer vision tasks without human annotation, through self-supervised techniques or unsupervised algorithms. Representative papers are highlighted.

News


Publications


Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
Tom Monnier, Matthew Fisher, Alexei A. Efros, Mathieu Aubry
arXiv 2022
paper | webpage | code | poster | bibtex

We present UNICORN 🦄, an unsupervised framework leveraging cross-instance consistency for high-quality 3D reconstructions from single-view images.

Representing Shape Collections with Alignment-Aware Linear Models
Romain Loiseau, Tom Monnier, Mathieu Aubry, Loïc Landrieu
3DV 2021
paper | webpage | code | bibtex

We characterize 3D shapes as affine transformations of linear families learned without supervision, and showcase its advantages on large shape collections.

Unsupervised Layered Image Decomposition into Object Prototypes
Tom Monnier, Elliot Vincent, Jean Ponce, Mathieu Aubry
ICCV 2021
paper | webpage | code | video | slides | poster | bibtex

An unsupervised learning framework to decompose images into object layers modeled as transformations of learnable sprites.

Deep Transformation-Invariant Clustering
Tom Monnier, Thibault Groueix, Mathieu Aubry
NeurIPS 2020 (oral presentation)
paper | webpage | code | video | slides | poster | bibtex

A simple and interpretable approach to clustering that jointly learns prototypes and their transformations to match data.

docExtractor: An off-the-shelf historical document element extraction
Tom Monnier, Mathieu Aubry
ICFHR 2020 (oral presentation)
paper | webpage | code | demo | video | slides | bibtex

Leveraging synthetic data and segmentation networks for generic element extraction in historical document images.

A web application for watermark recognition
O. Bounou, T. Monnier, I. Pastrolin, X. Shen, C. Bénévent and others
JDMDH 2020
paper | web application | related paper (Shen et al.)

New public web application dedicated to automatic watermark recognition.

Reviews, Teaching & Code


Open source projects

dti-clusteringdocExtractorunicorndti-spritesproject-webpage

Work experience


© You are welcome to copy this website"s code for your personal use, please attribute the source with a link back to this page and remove analytics in the header.
This template is inspired from great webpages I like such as this one, this one or this one. Possible misspellings: tom monier, tom monnie, tom monie, monniert.

Last update: May 2022