Adrien Bartoli has been a full Professor of Computer Science at Université d’Auvergne since fall 2009. He is currently leading the ALCoV (Advanced Laparoscopy and Computer Vision) research group jointly with Prof. Michel Canis. He is holding an ERC Consolidator Grant (2013-2017). Previously, he was a permanent CNRS research scientist at LASMEA since fall 2004 where he led ComSee, the Computer Vision research group, together with Thierry Chateau. He was a Visiting Professor in DIKU at the University of Copenhagen between 2006-2009 and a postdoctoral researcher in the Visual Geometry Group at the University of Oxford under Prof. Andrew Zisserman in 2004. Adrien Bartoli obtained his Habilitation Degree (HDR) from Université Blaise Pascal in June 2008. He completed his PhD in the Perception group at INRIA Grenoble under Prof. Peter Sturm and Prof. Radu Horaud. Adrien Bartoli has received several awards including the 2008 national CNRS médaille de bronze, the 2004 Grenoble-INP PhD thesis prize, the 2007 best student paper award at CORESA jointly with his student Vincent Gay-Bellile and colleague Patrick Sayd and the 2012 audience award at IPCAI with his colleague Toby Collins. He received an outstanding reviewer award at ECCV’08 and CVPR’10.

Adrien Bartoli’s main research interests include image registration and Shape-from-X for rigid and non-rigid scenarios, and machine learning within the field of theoretical and medical Computer Vision. He has published approximately 100 scientific papers and has been on the program committees for top-ranking conferences in the field. He has had roles in the organization of international events, including, General co-Chair for the workshops DEFORM (BMVC'06), NORDIA (CVPR'08 and CVPR'11), QU3ST (ECCV'12) and the 3DPVT’10 conference. He participated in the organization of tutorials at ISMAR'07, IROS'08, SCIA'11, ICCV'11 and was Publication Chair for 3DPVT’08.

News

Available Positions

PhD and postdoc in computer vision starting september/october 2012 - Contact me for more details

News Archive

May, 2011
Tutorial on Computer Vision in a Non-Rigid World @ ICCV'11
We are proud to announce that we'll give a full-day tutorial at ICCV'11! details coming soon... [more]

December, 2010
Tutorial on Computer Vision in a Non-Rigid World @ SCIA'11
This half-day tutorial is the third edition in a series of tutorials on the theme of deformable 3D reconstruction in computer vision. The recent approaches to Non-Rigid Structure-from-Motion and template-based reconstruction form a basis for the contents that also address the key problem of deformable image registration. [more]

November, 2010
Second Tutorial on Computer Vision in a Non-Rigid World @ IIT
This two day tutorial will be held in Genoa on Dec. 6-7. This tutorial presents recent computer vision techniques to deal with the challenging scenario of the inference and registration of a non-rigid object shape from a set of images taken by a camera. This problem is nowadays of central interest in fields such as medical imaging analysis, video-surveillance and human motion modelling. [more]

July, 2009
3DPVT'10 will be held in Paris in May'10!
Check out the conference website for more details.

March, 2009
Tutorial on Computer Vision in a Non-Rigid World @ ISR
This full day tutorial will be held in Lisbon on Apr. 20. This tutorial presents recent computer vision techniques to deal with the challenging scenario of the inference and registration of a non-rigid object shape from a set of images taken by a camera. This problem is nowadays of central interest in fields such as medical imaging analysis, video-surveillance and human motion modelling. [more]

May, 2008
Tutorial on Vision for Robotics @ IROS'08
This full day tutorial will be held in Nice on Sep. 22. We aim to give a survey of recent developments in computer vision for robotics applications... [more]

May, 2008
3DPVT'08 - Int'l Symposium on 3D Data Processing, Visualization and Transmission
This symposium was held in GeorgiaTech, Atlanta. See the website, including the online paper and video proceedings!

November 11, 2007
NORDIA'08 - Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment
This workshop will be held in Conjunction with CVPR'08 in Anchorage, Alaska on June 27-28. Send your papers before March 15 through the website!

November 9, 2007
`Gestion des auto-occultations pour l'augmentation d'une surface déformable' receives the best student paper award at CORESA'07.

October, 2007
Tutorial at ISMAR'07: Computer Vision for AR: Rigid and Deformable Tracking using Markers and Scene Features
In this tutorial, we aim to give a survey of the most recent developments on visual tracking in Augmented Reality applications... [more]

October 6, 2006
DIRT - Direct Image Registration Toolkit - v1.1
Building on the dual inverse compositional algorithm we proposed, DIRT efficiently registers pairs of color or grey-level images by jointly computing a geometric and a photometric transformation... [more]

April, 2006
DEFORM'06 - Workshop on Image Registration in Deformable Environments
This workshop will be held at BMVC'06, Edinburgh, UK on the 8th of September 2006. Its aim is to bring together researchers from communities working on deformable surface registration: computer vision, medical imaging, augmented reality... [more]. See the on-line proceedings.

ORASIS'05

January, 2005
ORASIS'05 - Congrès francophone des jeune chercheurs en vision par ordinateur
ComSee organized the French conference for young researchers in Computer Vision close to Clermont-Ferrand in May 2006. See the on-line proceedings.

Some of my Papers, by topics (complete list)

Deformable Model Complexity Tuning and Estimation
(applied to computer vision ; cross-validation, L-Tangent Norm, etc.)

Ad hoc warp complexity selection:

WBIR'12	Constant Flow Sampling: A Method to Automatically Select the Regularization Parameter in Image Registration
VMV'10	Pixel-Based Hyperparameter Selection for Feature-Based Image Registration
	We compute the M-estimator's scale, the warp's number of control points and the smoothing weight by combining feature-based and pixel-based approaches! we also have a finite step sampling scheme for the regularization weight.

Cross-validation for Linear Least Squares:

IJCV'09	On Computing the Prediction Sum of Squares Statistic in Linear Least Squares Problems with Multiple Parameter or Measurement Sets
JMIV'08	Maximizing the Predictivity of Smooth Deformable Image Warps Through Cross-Validation

Cross-validation for Nonlinear Least Squares:

ECCV'08

Efficient Camera Smoothing in Sequential Structure-from-Motion using Approximate Cross-Validation

The L-Tangent Norm criterion:

3DPVT'08

L-Tangent Norm: A Low Computational Cost Criterion for Choosing Regularization Weights and its Use for Range Surface Reconstruction

(joint image matching and 3D surface recovery)

ETFS'13	Image Registration Algorithm for Molecular Tagging Velocimetry Applied in Hele-Shaw Cell
4DMOD'11	A Pixel-Based Approach to Template-Based Monocular 3D Reconstruction of Deformable Surfaces

Deformable Surface Registration
(matching, feature- and pixel-based registration, etc.)

IJCV'12	Feature-Based Non-Rigid Surface Detection with Self-Occlusion Reasoning
IJCV'11	Feature-Driven Direct Non-Rigid Image Registration
PAMI'09	Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning
BMVC'08	Contour-Based Registration and Retexturing of Cartoon-Like Videos
BMVC'04	Direct Estimation of Non-Rigid Registrations

Deformable Structure-from-Motion
(low-rank shape model, paper surface, template-based, etc.)

BMVC'12	Deformable 3D Reconstruction with an Object Database
CAVW'12	A Computational Model of Bounded Developable Surfaces with Application to Image-Based 3D Reconstruction
CVPR'12	On Template-Based Reconstruction from a Single View: Analytical Solutions and Proofs of Well-Posedness for Developable, Isometric and Conformal Surfaces
ICCV'11	Multiview 3D Warps
VMV'10	Locally Affine and Planar Deformable Surface Reconstruction from Video
ACCV'10	Monocular Template-based Reconstruction of Smooth and Inextensible Surfaces
IJCV'11	Monocular Template-Based Reconstruction of Inextensible Surfaces
ECCV'10	Sequential Non-Rigid Structure-from-Motion with the 3D-Implicit Low-Rank Shape Model
NORDIA'08	Template-Based Paper Reconstruction from a Single Image is Well Posed when the Rulings are Parallel
CVPR'08	Coarse-to-Fine Low-Rank Structure-from-Motion
JMIV'08	Implicit Non-Rigid Structure-from-Motion with Priors
CVIU'05	The Geometry of Dynamic Scenes - On Coplanar and Convergent Linear Motions Embedded in 3D Static Scenes
WDV'05	A Batch Algorithm For Implicit Non-Rigid Shape and Motion Recovery
WDV'05	Estimating the Pose of a 3D Sensor in a Non-Rigid Environment

Other Work
(Procrustes analyis, TOF cameras, keypoints, etc.)

ECCV'12	KAZE Features
BMVC'12	Depth Correction for Depth Cameras From Planarity
QU3ST'12	Noise Modelling and Uncertainty Propagation for TOF Sensors
3DIMPVT'12	Calibrating an Optical See-Through Rig with Two Non-Overlapping Cameras: the Virtual Camera Framework
IJCV'13	Stratified Generalized Procrustes Analysis
ICIP'12	Non-Parametric Depth Calibration of a TOF Camera
CVPR'11	Global Optimization for Optimal Generalized Procrustes Analysis
MIUA'11	3D Medical Image Enhancement based on Wavelet Transforms
WMVC'11	Closed-Form Solutions to Multiple-View Homography Estimation
3DPVT'10	Single-View Perspective Shape-from-Texture with Focal Length Estimation

Image Registration, Active Appearance Models
(inverse composition, light invariance, faces, etc.)

VMV'10	Direct Image Registration without Region of Interest
BMVC'08	Pools of AAMs: Towards Automatically Fitting Any Face Image
PAMI'08	Groupwise Geometric and Photometric Direct Image Registration
CVPR'08	Light-Invariant Fitting of Active Appearance Models
BMVC'07	Segmented AAMs Improve Person-Independent Face Fitting
SCIA'07	Shadow Resistant Direct Image Registration

3DIM'07

Joint Reconstruction and Registration of a Deformable Planar Surface Observed by a 3D Sensor

CAVW'04

Motion Panoramas

(Rigid) Structure-from-Motion for Points
(fundamental matrix, bundle adjustment, etc.)

ECCV'12	Global Optimization of Object Pose and Motion from a Single Rolling Shutter Image with Automatic 2D-3D Matching
3DPVT'10	Bi-Objective Bundle Adjustment With Application to Multi-Sensor SLAM
3DPVT'10	A Generic Rolling Shutter Camera Model and its Application to Dynamical Pose Estimation
ICCV'09	Is Dual Linear Self-Calibration Artificially Ambiguous?
BMVC'09	Algebraic Line Search for Bundle Adjustment
WMVC'09	Simultaneous Motion Estimation and Point Matching Using Geometric Cues Only
ECCV'08	Efficient Camera Smoothing in Sequential Structure-from-Motion using Approximate Cross-Validation
CVPR'07	Algorithms for Batch Matrix Factorization with Application to Structure-from-Motion
CVPR'07	On Constant Focal Length Self-Calibration From Multiple Views
IJCV'06	Affine Approximation for Direct Batch Recovery of Euclidean Motion From Sparse Data
EMM CVPR'05	Handling Missing Data in the Computation of 3D Affine Transformations
PAMI'04	Non-Linear Estimation of the Fundamental Matrix With Minimal Parameters

(Rigid) Structure-from-Motion for Lines
(triangulation, points-on-line, etc.)

IVC'07	Triangulation for Points on Lines
CVPR'07	Kinematics From Lines in a Single Rolling Shutter Image
CVIU'05	Structure-From-Motion Using Lines: Representation, Triangulation and Bundle Adjustment
ECCV'04	A Framework For Pencil-of-Points Structure-From-Motion
IJCV'04	The 3D Line Motion Matrix and Alignment of Line Reconstructions
CVPR'03	Motion From 3D Line Correspondences: Linear and Non-Linear Solutions

(Rigid) Structure-from-Motion for Planes
(piecewise planar scenes, segmentation, etc.)

CVIU'07	A Random Samping Strategy For Piecewise Planar Scene Segmentation
IJCV'03	Constrained Structure and Motion From Multiple Uncalibrated Views of a Piecewise Planar Scene

(Rigid) Structure-from-Motion for Curves
(triangulation, quality control, etc.)

WISP'07	Adaptive Evolution of 3D Curves for Quality Control
EMM CVPR'07	Energy-Based Reconstruction of 3D Curves for Quality Control
SCIA'07	Reconstruction of 3D Curves for Quality Control