Mathieu Aubry
He/Him

I am a senior researcher in the Imagine team of the LIGM lab at École des Ponts ParisTech (ENPC).

I am interested in computer vision with a focus on unsupervised image collection analysis (ERC DISCOVER), and applications to historical data (also ANR VHS and ANR EIDA ) and Earth imagery analysis. To get an overview of my research, you can look at the ANR EnHerit website (2017-2023).

Contact me if you are interested in historical data or earth imagery for M2/PhD ( 2023 internship offers ), research engineer and postoc positions.

Imagine  /  Email  /  CV  /  Bio  /  Google Scholar

profile photo
Students Publications Teaching Opinions
Students

Current PhD students:

Graduated:

Past Post-doc: Nicolas Gonthier (now IPEF working at IGN)

Publications

Representative papers are highlighted.

Abstracts for our VHS and EIDA projects building vision tools for historians
Z. S. Baltci, S. Kalleli, F. Aouinti, A. Guilbaud, S. Lazaris, S. Trigg, S. Albouy, S. Gessner, M. Husson, M. Aubry, presented at IAMAHA 2023
VHS | EIDA

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives
T. Monnier, J. Austin, A. Kanazawa, A. Efros, M. Aubry
NeurIPS 2023
paper | project page

Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans
R. Loiseau, E. Vincent, M. Aubry, L. Landrieu
ArXiv 2023
paper | project page

Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach
E. Vincent, J. Ponce, M. Aubry
ArXiv 2023
paper | project page

The Learnable Typewriter A Generative Approach to Text Line Analysis
Y. Siglidis, N. Gonthier, J. Gaubil, T. Monnier, M. Aubry
ArXiv 2023
paper | project page

MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
Y. Labbé, L. Manuelli, A. Mousavian, S. Tyree, S. Birchfield, J. Tremblay, J. Carpentier, M. Aubry, D. Fox, J. Sivic
CoRL 2022
paper | project page

A Model You Can Hear: Audio Classification with Playable Prototypes
R. Loiseau, B. Bouvier, Y. Teytaut, E. Vincent, M. Aubry, L. Landrieu
ISMIR 2022, CVPRw 2022
paper | project page

Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
T. Monnier, M. Fisher, A. Efros, M. Aubry
ECCV 2022
paper | project page

Online Segmentation of LiDAR Sequences: Dataset and Algorithm
R. Loiseau, M. Aubry, L. Landrieu
ECCV 2022
paper | project page

Learning joint surface atlases
T. Deprelle, T. Groueix, N. Aigerman, V. Kim, M. Aubry
ArXiv 2022
paper | project page

NeuralWarp: Improving neural implicit surfaces geometry with patch warping
F. Darmon, B. Bascle, J.-C. Devaux, P. Monasse, M. Aubry
CVPR 2022
paper | project page

Focal Length and Object Pose Estimation via Render and Compare
G. Ponimatkin, Labbé, B. Russell, M. Aubry, J. Sivic
CVPR 2022
paper | project page

Spatially-consistent Feature Matching and Learning for Heritage Image Analysis
X. Shen, R. Champenois, S. Ginosar, I. Pastrolin, M. Rousselot, O. Bounou, T. Monnier, S. Gidaris, F. Bougard, P.-G. Raverdy, M.-F. Limon, C. Bénévent, M. Smith, O. Poncet, K. Bender, B. Joyeux-Prunel, E. Honig, A. Efros, M. Aubry
IJCV 2022
paper | project page

Re-ranking for image retrieval and transductive few-shot classification
X. Shen, Y. Xiao, S. Hu, O. Sbai, M. Aubry
NeurIPS 2021
paper | project page

Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
X. Shen, A. Efros, A. Joulin, M. Aubry
ArXiv 2021, CVPR 2022 workshops
paper | project page

Representing Shape Collections with Alignment-Aware Linear Models
R. Loiseau, T. Monnier, M. Aubry, L. Landrieu
3DV 2021
paper | project page

Unsupervised Layered Image Decomposition into Object Prototypes
T. Monnier, E. Vincent, J. Ponce, M. Aubry
ICCV 2021
paper | project page

Image Collation: Matching illustrations in manuscripts
R. Kaoua, X. Shen, A. Durr, S. Lazaris, D. Picard, M. Aubry
ICDAR 2021
paper | project page

Deep Multi-View Stereo gone wild
F. Darmon, B. Bascle, J.-C. Devaux, P. Monasse, M. Aubry
3DV 2021
paper | project page

Single-view robot pose and joint angle estimation via render & compare
Y. Labbé, J. Carpentier, M. Aubry, J. Sivic
CVPR 2021
paper | project page

Learning to Guide Local Feature Matches
F. Darmon, M. Aubry , P. Monasse
3DV 2020
paper | project page

Spherical Perspective on Learning with Batch Norm
S. Roburin, Y.de Mont-Marin, A. Bursuc, R.Marlet, P. Perez, M. Aubry
ArXiv 2020, Neurocomputing 2022
paper | project page

Deep Transformation-Invariant Clustering
T. Monnier, T. Groueix, M. Aubry
NeurIPS 2020
paper | project page

docExtractor: An off-the-shelf historical document element extraction
T. Monnier, M. Aubry
ICFHR 2020
paper | project page

CosyPose: Consistent multi-view multi-object 6D pose estimation
Y. Labbé, J. Carpentier, M. Aubry, J. Sivic
ECCV 2020
paper | project page

Impact of base dataset design on few-shot image classification
O. Sbai, C. Couprie, M. Aubry
ECCV 2020
paper | project page

RANSAC-Flow: generic two-stage image alignment
X. Shen, F. Darmon, A. Efros, M. Aubry
ECCV 2020
paper | project page

Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning
Y. Labbé, S. Zagoruyko, I. Kalevatykh, I. Laptev, J. Carpentier, M. Aubry, J. Sivic
RAL 2020
paper | project page

Large-Scale Historical Watermark Recognition:dataset and a new consistency-based approach
X. Shen, I. Pastrolin, O. Bounou, S. Gidaris, M. Smith, O. Poncet, M. Aubry
ICPR 2020
paper | project page | Web App | paper on Web App

Bilinear image translation for temporal analysis of photo collections
T. Dalens, M. Aubry, J. Sivic
TPAMI 2019
paper

Learning elementary structures for 3D shape generation and matching
T. Deprelle, T. Groueix, M. Fisher, V. G. Kim, B. C. Russell, M. Aubry
NeurIPS 2019
paper | project page

Unsupervised Image Decomposition in Vector Layers
O. Sbai, C. Couprie, M. Aubry
ArXiv 2019 / ICIP 2020
paper | project page

Deep Pose Estimation for Arbitrary 3D Objects
Y. Xiao, X. Qiu, P-A Langlois M. Aubry, R. Marlet
BMVC 2019
paper | project page

Unsupervised cycle-consistent deformation for shape matching
T. Groueix, M. Fisher, V. G. Kim, B. C. Russell, M. Aubry
SGP 2019
paper | project page

Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
X. Shen, A. Efros, M. Aubry
CVPR 2019
paper | project page

3D-CODED : 3D Correspondences by Deep Deformation
T. Groueix, M. Fisher, V. G. Kim, B. C. Russell, M. Aubry
ECCV 2018
paper | project page

Virtual Training for a Real Application: Accurate Object-Robot Relative Localization without Calibration
V. Loing, R. Marlet, M. Aubry
IJCV 2018
paper | project page

AtlasNet: A Papier-Mâché Approach to Learning Surface Generation
T. Groueix, M. Fisher, V. G. Kim, B. C. Russell, M. Aubry
CVPR 2018
paper | project page

3D Sketching using Multi-View Deep Volumetric Prediction
J. Delanoy, M. Aubry, P. Isola, A. Efros, A. Bousseau
I3D 2018
paper | project page

Crafting a multi-task CNN for viewpoint estimation
F. Massa, R. Marlet and M. Aubry
BMVC 2016
paper | project page

Automatic 3D Car Model Alignment for Mixed Image-Based Rendering
R. Ortiz-Cayon, A. Djelouah, F. Massa, M. Aubry, G. Drettakis
3DV 2016
paper | project page

Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views
F. Massa, B. Russell and M. Aubry
CVPR 2016
paper | project page

Learning Dense Correspondence via 3D-guided Cycle Consistency
T. Zhou, P. Krähenbühland, M. Aubry, Q. Huang, and A. Efros
CVPR, 2016
paper | project page

Dex-Net 1.0: A Cloud-Based Network of 3D Objects for Robust Grasp Planning Using a Multi-Armed Bandit Model with Correlated Rewards
J. Mahler, F. Pokorny, B. Hou, M. Roderick, M. Laskey, M. Aubry, K. Kohlhoff, T. Kroeger, J. Kuffner, K. Goldberg
ICRA, 2016
paper

Understanding deep features with computer-generated imagery
M. Aubry and B. Russell
ICCV, 2015
paper | project page

Visual geo-localization of non-photographic depictions via 2D-3D alignment
M. Aubry, B. Russell and J. Sivic
Springer book chapter on Visual Analysis and Geo-Localization of Large Scale Imagery, 2015
paper

Anisotropic Laplace-Beltrami Operators for Shape Analysis
M. Andreux, E. Rodolà, M. Aubry, and D. Cremers
Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA), 2014
paper | project page

Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models
M. Aubry, D. Maturana, A. Efros, B. Russell and J. Sivic
CVPR, 2014
paper | project page

Painting-to-3D Model Alignment Via Discriminative Visual Elements
M. Aubry, B. Russell and J. Sivic
ACM Transactions on Graphics, 2014 (presented at SIGGRAPH 2014)
paper | project page

Fast and Robust Pyramid-based Image Processing thumbnail Fast Local Laplacian Filters: Theory and Applications
M. Aubry, S. Paris, S. Hasinoff, J. Kautz, F. Durand
ACM Transactions on Graphics, 2014 (presented at SIGGRAPH 2014)
paper | project page

A Super-resolution Framework for High-Accuracy Multiview Reconstruction A Super-resolution Framework for High-Accuracy Multiview Reconstruction
B. Goldluecke, M. Aubry, K. Kolev, D. Cremers
IJCV 2014
paper

Decoupling Photometry and Geometry in Dense
Variational Camera Calibration thumbnail Decoupling Photometry and Geometry in Dense Variational Camera Calibration
M. Aubry, K. Kolev, B. Goldluecke, D. Cremers
ICCV 2011
paper

Pose-Consistent 3D Shape Segmentation Based on a
Quantum Mechanical Feature Descriptor thumbnail Pose-Consistent 3D Shape Segmentation Based on a Quantum Mechanical Feature Descriptor
M. Aubry, U. Schlickewei, D. Cremers
Pattern Recognition (Proc. DAGM), Springer, 2011
paper | project page

The Wave Kernel Signature: A Quantum Mechanical
Approach To Shape Analysis thumbnail The Wave Kernel Signature: A Quantum Mechanical Approach To Shape Analysis
M. Aubry, U. Schlickewei, D. Cremers
ICCV workshop on Dynamic Shape Capture and Analysis (4DMOD) 2011
paper | project page

Teaching

Opinions

The following links are a random collection of personal opinions, but you might want to have a look if you are interested in working with me, or are just curious. Note I am not an expert on any of these topics, feel free to send feedback or suggestions.

Projects

  • 2015-2019: RAPID Tabasco project on low-supervision deep learning
  • 2017-2018: France-Berkeley-Fund grant on Enhancing Heritage Image Databases
  • 2018-2021: CIFRE PhD with Camille Couprie at Facebook AI Research
  • 2018-2022: ANR JCJC EnHerit project on enhancing heritage image databases
  • 2019-2022: CIFRE PhD with Patrick Perez and Renaud Marlet at Valeo AI
  • 2021-2025: ANR VHS project on historical scientific illustrations
  • 2022-2026: ANR EIDA project on historical astronomical diagrams
  • 2023-2028: ERC starting grant DISCOVER on visual structures discovery
Contact

IMAGINE/LIGM
École des Ponts ParisTech
6-8, Av Blaise Pascal - Cité Descartes
Champs-sur-Marne
77455 Marne-la-Vallée cedex 2

email: mathieu [dot] aubry [at] imagine [dot] enpc [dot] fr
phone: +33 (0)1 64 15 21 74

Top  /  Imagine  /  Email  /  CV  /  Bio  /  Google Scholar


Website stolen from Jon Barron.