Tom Monnier

PhD student at Imagine - ENPC

I am a final-year PhD student working on unsupervised learning under the guidance of Mathieu Aubry (ENPC). During my PhD, I was fortunate to work with Jean Ponce (Inria - WILLOW), Matthew Fisher (Adobe Research) and Alexei Efros (UC Berkeley). Before that, I completed my engineer's degree (=M.Sc.) at Mines Paris.

My research currently focuses on building self-supervised and unsupervised machines to solve visual tasks without manual annotation. Representative papers are highlighted.

email.google scholar.github.

News

Publications

MACARONS: Mapping And Coverage Anticipation with RGB Online Self-supervision
Antoine Guédon, Tom Monnier, Pascal Monasse, Vincent Lepetit
CVPR 2023
paper | webpage | code | video | slides | bibtex

We introduce MACARONS, a method that learns in a self-supervised fashion to explore new environments and reconstruct them in 3D using RGB images only.

The Learnable Typewriter: A Generative Approach to Text Line Analysis
Ioannis Siglidis, Nicolas Gonthier, Julien Gaubil, Tom Monnier, Mathieu Aubry
arXiv 2023
paper | webpage | code | bibtex

We build upon unsupervised sprite-based image decomposition approaches to design a generative method to character analysis and recognition in text lines.

Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?
Monika Wysoczanska, Tom Monnier, Tomasz Trzcinski, David Picard
NeurIPS Workshops 2022
paper | bibtex

A Transformer-based framework to evaluate off-the-shelf features (object-centric and dense representations) for the reasoning task of VQA.

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

We present UNICORN 🦄, an unsupervised approach 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 | 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 | 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 | video | slides | bibtex

Leveraging synthetic data and segmentation networks for generic element extraction in historical document images.

Academic activities

Invited talks

© You are welcome to copy the code, please attribute the source with a link back to this page.
Template inspired from [1], [2], [3]. Misspellings: monier, monnie, monie, monniert.

Last updated: March 2023