Mathieu Aubry

Mathieu Aubry

Auto-generated profile, based on publicly available information

Mathieu Aubry

LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2011
Verified
Conference Paper
Closed access
MAMathieu Aubry
Mathieu Aubry
USUlrich Schlickewei
Ulrich Schlickewei
DCDaniel Cremers
Daniel Cremers
We introduce the Wave Kernel Signature (WKS) for characterizing points on non-rigid three-dimensional shapes. The WKS represents the average probability of measuring a quantum mechanical particle at a specific location. By letting vary the energy of the particle, the WKS encodes and separates information from various different Laplace eigenfrequencies. This clear scale separation makes the WKS well suited for a large variety of applications. Both theoretically and in quantitative experiments we demonstrate that the WKS is substantially more discriminative and therefore allows for better feature matching than the commonly used Heat Kernel Signature (HKS). As an application of the WKS in shape analysis we show results on shape matching.

1 June 2014
Verified
Conference Paper
Closed access
MAMathieu Aubry
Mathieu Aubry
DMDaniel Maturana
Daniel Maturana
AEAlexei A. Efros
Alexei A. Efros
BRBryan C. Russell
Bryan C. Russell
JSJosef Sivic
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. Using the "chair" class as a running example, we propose an exemplar-based 3D category representation, which can explicitly model chairs of different styles as well as the large variation in viewpoint. We develop an approach to establish part-based correspondences between 3D CAD models and real photographs. This is achieved by (i) representing each 3D model using a set of view-dependent mid-level visual elements learned from synthesized views in a discriminative fashion, (ii) carefully calibrating the individual element detectors on a common dataset of negative images, and (iii) matching visual elements to the test image allowing for small mutual deformations but preserving the viewpoint and style constraints. We demonstrate the ability of our system to align 3D models with 2D objects in the challenging PASCAL VOC images, which depict a wide variety of chairs in complex scenes.

1 June 2016
Verified
Conference Paper
Closed access
TZTinghui Zhou
Tinghui Zhou
PKPhilipp Krahenbuhl
Philipp Krahenbuhl
MAMathieu Aubry
Mathieu Aubry
QHQixing Huang
Qixing Huang
AEAlexei A. Efros
Alexei A. Efros
Discriminative deep learning approaches have shown impressive results for problems where human-labeled ground truth is plentiful, but what about tasks where labels are difficult or impossible to obtain? This paper tackles one such problem: establishing dense visual correspondence across different object instances. For this task, although we do not know what the ground-truth is, we know it should be consistent across instances of that category. We exploit this consistency as a supervisory signal to train a convolutional neural network to predict cross-instance correspondences between pairs of images depicting objects of the same category. For each pair of training images we find an appropriate 3D CAD model and render two synthetic views to link in with the pair, establishing a correspondence flow 4-cycle. 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. At test time, no CAD models are required. We demonstrate that our end-to-end trained ConvNet supervised by cycle-consistency outperforms state-of-the-art pairwise matching methods in correspondence-related tasks.

1 May 2016
Verified
Conference Paper
Closed access
JMJeffrey Mahler
Jeffrey Mahler
FPFlorian T. Pokorny
Florian T. Pokorny
BHBrian Hou
Brian Hou
MRMelrose Roderick
Melrose Roderick
MLMichael Laskey
Michael Laskey
KGKen Goldberg
Ken Goldberg
This paper presents the Dexterity Network (Dex-Net) 1.0, a dataset of 3D object models and a sampling-based planning algorithm to explore how Cloud Robotics can be used for robust grasp planning. The algorithm uses a Multi- Armed Bandit model with correlated rewards to leverage prior grasps and 3D object models in a growing dataset that currently includes over 10,000 unique 3D object models and 2.5 million parallel-jaw grasps. Each grasp includes an estimate of the probability of force closure under uncertainty in object and gripper pose and friction. Dex-Net 1.0 uses Multi-View Convolutional Neural Networks (MV-CNNs), a new deep learning method for 3D object classification, to provide a similarity metric between objects, and the Google Cloud Platform to simultaneously run up to 1,500 virtual cores, reducing experiment runtime by up to three orders of magnitude. Experiments suggest that correlated bandit techniques can use a cloud-based network of object models to significantly reduce the number of samples required for robust grasp planning. We report on system sensitivity to variations in similarity metrics and in uncertainty in pose and friction. Code and updated information is available at http://berkeleyautomation.github.io/dex-net/.

25 July 2018 in Proceedings of the ACM on Computer Graphics and Interactive Techniques
Verified
Journal Article
Open access
PDF file
JDJohanna Delanoy
Johanna Delanoy
MAMathieu Aubry
Mathieu Aubry
PIPhillip Isola
Phillip Isola
AEAlexei A. Efros
Alexei A. Efros
ABAdrien Bousseau
Adrien Bousseau
Sketch-based modeling strives to bring the ease and immediacy of drawing to the 3D world. However, while drawings are easy for humans to create, they are very challenging for computers to interpret due to their sparsity and ambiguity. We propose a data-driven approach that tackles this challenge by learning to reconstruct 3D shapes from one or more drawings. At the core of our approach is a deep convolutional neural network (CNN) that predicts occupancy of a voxel grid from a line drawing. This CNN provides an initial 3D reconstruction as soon as the user completes a single drawing of the desired shape. We complement this single-view network with an updater CNN that refines an existing prediction given a new drawing of the shape created from a novel viewpoint. A key advantage of our approach is that we can apply the updater iteratively to fuse information from an arbitrary number of viewpoints, without requiring explicit stroke correspondences between the drawings. We train both CNNs by rendering synthetic contour drawings from hand-modeled shape collections as well as from procedurally-generated abstract shapes. Finally, we integrate our CNNs in an interactive modeling system that allows users to seamlessly draw an object, rotate it to see its 3D reconstruction, and refine it by re-drawing from another vantage point using the 3D reconstruction as guidance.

1 December 2015
Verified
Conference Paper
Closed access
MAMathieu Aubry
Mathieu Aubry
BRBryan C. Russell
Bryan C. Russell
We introduce an approach for analyzing the variation of features generated by convolutional neural networks (CNNs) trained on large image datasets with respect to scene factors that occur in natural images. Such factors may include object style, 3D viewpoint, color, and scene lighting configuration. Our approach analyzes CNN feature responses with respect to different scene factors by controlling for them via rendering using a large database of 3D CAD models. The rendered images are presented to a trained CNN and responses for different layers are studied with respect to the input scene factors. We perform a linear decomposition of the responses based on knowledge of the input scene factors and analyze the resulting components. In particular, we quantify their relative importance in the CNN responses and visualize them using principal component analysis. We show qualitative and quantitative results of our study on three trained CNNs: AlexNet [18], Places [43], and Oxford VGG [8]. We observe important differences across the different networks and CNN layers with respect to different scene factors and object categories. Finally, we demonstrate that our analysis based on computer-generated imagery translates to the network representation of natural images.