Search Results for author: Mathieu Aubry

Found 42 papers, 23 papers with code

Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans

1 code implementation19 Apr 2023 Romain Loiseau, Elliot Vincent, Mathieu Aubry, Loic Landrieu

Our goal is to provide a practical tool for analyzing 3D scenes with unique characteristics in the context of aerial surveying and mapping, without relying on application-specific user annotations.

Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach

1 code implementation22 Mar 2023 Elliot Vincent, Jean Ponce, Mathieu Aubry

Improvements in Earth observation by satellites allow for imagery of ever higher temporal and spatial resolution.

Time Series Classification

The Learnable Typewriter: A Generative Approach to Text Analysis

1 code implementation3 Feb 2023 Ioannis Siglidis, Nicolas Gonthier, Julien Gaubil, Tom Monnier, Mathieu Aubry

Second, we show the potential of our method for new applications, more specifically in the field of paleography, which studies the history and variations of handwriting, and for cipher analysis.

Semantic Segmentation Unsupervised Text Recognition

MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare

no code implementations13 Dec 2022 Yann Labbé, Lucas Manuelli, Arsalan Mousavian, Stephen Tyree, Stan Birchfield, Jonathan Tremblay, Justin Carpentier, Mathieu Aubry, Dieter Fox, Josef Sivic

Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner.

6D Pose Estimation

Learning Joint Surface Atlases

no code implementations13 Jun 2022 Theo Deprelle, Thibault Groueix, Noam Aigerman, Vladimir G. Kim, Mathieu Aubry

We demonstrate that this improves the quality of the learned surface representation, as well as its consistency in a collection of related shapes.

Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

1 code implementation21 Apr 2022 Tom Monnier, Matthew Fisher, Alexei A. Efros, Mathieu Aubry

Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry.

3D Object Reconstruction From A Single Image 3D Reconstruction +1

Focal Length and Object Pose Estimation via Render and Compare

1 code implementation CVPR 2022 Georgy Ponimatkin, Yann Labbé, Bryan Russell, Mathieu Aubry, Josef Sivic

We introduce FocalPose, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object.

Pose Estimation Translation

Re-ranking for image retrieval and transductive few-shot classification

no code implementations NeurIPS 2021 Xi Shen, Yang Xiao, Shell Hu, Othman Sbai, Mathieu Aubry

In the problems of image retrieval and few-shot classification, the mainstream approaches focus on learning a better feature representation.

Classification Few-Shot Learning +3

Learning Co-segmentation by Segment Swapping for Retrieval and Discovery

1 code implementation29 Oct 2021 Xi Shen, Alexei A. Efros, Armand Joulin, Mathieu Aubry

The goal of this work is to efficiently identify visually similar patterns in images, e. g. identifying an artwork detail copied between an engraving and an oil painting, or recognizing parts of a night-time photograph visible in its daytime counterpart.

Graph Clustering Object Discovery +3

Representing Shape Collections with Alignment-Aware Linear Models

1 code implementation3 Sep 2021 Romain Loiseau, Tom Monnier, Loïc Landrieu, Mathieu Aubry

In this paper, we revisit the classical representation of 3D point clouds as linear shape models.

Image Collation: Matching illustrations in manuscripts

no code implementations18 Aug 2021 Ryad Kaoua, Xi Shen, Alexandra Durr, Stavros Lazaris, David Picard, Mathieu Aubry

For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other.

Deep Multi-View Stereo gone wild

1 code implementation30 Apr 2021 François Darmon, Bénédicte Bascle, Jean-Clément Devaux, Pascal Monasse, Mathieu Aubry

Deep multi-view stereo (MVS) methods have been developed and extensively compared on simple datasets, where they now outperform classical approaches.

Depth Estimation Depth Prediction

Unsupervised Layered Image Decomposition into Object Prototypes

1 code implementation ICCV 2021 Tom Monnier, Elliot Vincent, Jean Ponce, Mathieu Aubry

We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models.

Object Discovery

Single-view robot pose and joint angle estimation via render & compare

no code implementations CVPR 2021 Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic

We introduce RoboPose, a method to estimate the joint angles and the 6D camera-to-robot pose of a known articulated robot from a single RGB image.

docExtractor: An off-the-shelf historical document element extraction

1 code implementation15 Dec 2020 Tom Monnier, Mathieu Aubry

We present docExtractor, a generic approach for extracting visual elements such as text lines or illustrations from historical documents without requiring any real data annotation.

Document Layout Analysis

Learning to Guide Local Feature Matches

no code implementations21 Oct 2020 François Darmon, Mathieu Aubry, Pascal Monasse

We tackle the problem of finding accurate and robust keypoint correspondences between images.

3D Reconstruction

CosyPose: Consistent multi-view multi-object 6D pose estimation

3 code implementations ECCV 2020 Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic

Second, we develop a robust method for matching individual 6D object pose hypotheses across different input images in order to jointly estimate camera viewpoints and 6D poses of all objects in a single consistent scene.

6D Pose Estimation 6D Pose Estimation using RGB

Impact of base dataset design on few-shot image classification

no code implementations ECCV 2020 Othman Sbai, Camille Couprie, Mathieu Aubry

In this paper, we systematically study the effect of variations in the training data by evaluating deep features trained on different image sets in a few-shot classification setting.

Classification Few-Shot Image Classification +1

Deep Transformation-Invariant Clustering

1 code implementation NeurIPS 2020 Tom Monnier, Thibault Groueix, Mathieu Aubry

In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and performs clustering directly in image space.

Ranked #2 on Unsupervised Image Classification on SVHN (using extra training data)

Image Clustering Unsupervised Image Classification

Learning elementary structures for 3D shape generation and matching

3 code implementations NeurIPS 2019 Theo Deprelle, Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry

We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape.

Ranked #7 on 3D Dense Shape Correspondence on SHREC'19 (using extra training data)

3D Dense Shape Correspondence 3D Shape Generation +1

Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning

2 code implementations23 Apr 2019 Yann Labbé, Sergey Zagoruyko, Igor Kalevatykh, Ivan Laptev, Justin Carpentier, Mathieu Aubry, Josef Sivic

We address the problem of visually guided rearrangement planning with many movable objects, i. e., finding a sequence of actions to move a set of objects from an initial arrangement to a desired one, while relying on visual inputs coming from an RGB camera.

Virtual Training for a Real Application: Accurate Object-Robot Relative Localization without Calibration

no code implementations7 Feb 2019 Vianney Loing, Renaud Marlet, Mathieu Aubry

Localizing an object accurately with respect to a robot is a key step for autonomous robotic manipulation.

Unsupervised Image Decomposition in Vector Layers

no code implementations13 Dec 2018 Othman Sbai, Camille Couprie, Mathieu Aubry

Deep image generation is becoming a tool to enhance artists and designers creativity potential.

Image Generation Image Reconstruction +3

3D-CODED: 3D Correspondences by Deep Deformation

no code implementations ECCV 2018 Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry

By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template.

3D-CODED : 3D Correspondences by Deep Deformation

1 code implementation13 Jun 2018 Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry

By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template.

Ranked #8 on 3D Dense Shape Correspondence on SHREC'19 (using extra training data)

3D Dense Shape Correspondence 3D Human Pose Estimation +2

3D Sketching using Multi-View Deep Volumetric Prediction

no code implementations26 Jul 2017 Johanna Delanoy, Mathieu Aubry, Phillip Isola, Alexei A. Efros, Adrien Bousseau

The main strengths of our approach are its robustness to freehand bitmap drawings, its ability to adapt to different object categories, and the continuum it offers between single-view and multi-view sketch-based modeling.

3D Reconstruction

Crafting a multi-task CNN for viewpoint estimation

no code implementations13 Sep 2016 Francisco Massa, Renaud Marlet, Mathieu Aubry

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation.

General Classification Viewpoint Estimation

Learning Dense Correspondence via 3D-guided Cycle Consistency

no code implementations CVPR 2016 Tinghui Zhou, Philipp Krähenbühl, Mathieu Aubry, Qi-Xing Huang, Alexei A. Efros

We use ground-truth synthetic-to-synthetic correspondences, provided by the rendering engine, to train a ConvNet to predict synthetic-to-real, real-to-real and real-to-synthetic correspondences that are cycle-consistent with the ground-truth.

Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views

no code implementations CVPR 2016 Francisco Massa, Bryan Russell, Mathieu Aubry

This paper presents an end-to-end convolutional neural network (CNN) for 2D-3D exemplar detection.

Understanding deep features with computer-generated imagery

no code implementations ICCV 2015 Mathieu Aubry, Bryan Russell

The rendered images are presented to a trained CNN and responses for different layers are studied with respect to the input scene factors.

Convolutional Neural Networks for joint object detection and pose estimation: A comparative study

no code implementations22 Dec 2014 Francisco Massa, Mathieu Aubry, Renaud Marlet

In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose.

General Classification object-detection +2

Seeing 3D Chairs: Exemplar Part-based 2D-3D Alignment using a Large Dataset of CAD Models

no code implementations CVPR 2014 Mathieu Aubry, Daniel Maturana, Alexei A. Efros, Bryan C. Russell, Josef Sivic

This paper poses object category detection in images as a type of 2D-to-3D alignment problem, utilizing the large quantities of 3D CAD models that have been made publicly available online.

Cannot find the paper you are looking for? You can Submit a new open access paper.