PhD in Computer Graphics

Job opening

We are looking to hire

Our Computer Graphics group is composed of two permanents (Pr. Tamy Boubekeur and me), 3 PhD candidates in rendering, 4 PhD candidates in geometry processing and modeling. We also have close collaborations with Dr. Pooran Memari and Dr. Maks Ovsjanikov, and the various teams of the Image, Data, Signals Department of Telecom-ParisTech.

Telecom-ParisTech is located in the heart of the lovely 13th district of Paris.

Feel free to contact me by mail if you are interested.

About me

Hi! I'm Jean-Marc. I work mainly in Computer Graphics, on the topics of Shape Modeling, Geometry Processing, Animation, Shape Analysis and Deformation, but I always try to expand my area of expertise and I'm interested in all aspects related to Computer Graphics and Data Processing and Analysis in general. I received my PhD in 2012 in the Computer Graphics group of Telecom-ParisTech, which is a first class engineering school located in the core of Paris, in the XIIIth district. I have worked from 2013 to 2015 as a post-doctoral researcher at Telecom ParisTech and at TU Delft and I am since september 2016 an associate professor in Computer Graphics at Telecom ParisTech.

Here are my updated CV and my scholar page.
Feel free to contact me at jean-marc.thiery _at_
Domains of interest
- Geometric Modeling
- Geometry Processing
- Computational Geometry
- Shape Animation
... Mathematics , Computer Graphics , and Computer Science in general
Previous jobs

- September 2016 - present day:
Associate Professor at Telecom-Paristech.

- September 2015 - August 2016:

- February 2014 - August 2015:
Post-doc at TU Delft on geometric modeling and geometry processing.

- December 2012 - December 2013:
Post-doc at Telecom-Paristech on geometric modeling and geometry processing.

- October 2009 - november 2012 :
PhD thesis at Telecom-Paristech on the subject of "Digital Geometry and Algorithmic Geometry for Interactive 3D Design" , under the direction of Pr. Tamy Boubekeur.

Contributions (see also scholar)
We present a fast, robust and high-quality technique to skin a mesh with reference to a skeleton. We consider the space of possible skeleton deformations (based on skeletal constraints, or skeletal animations), and compute skinning weights based on an optimization scheme to obtain as-rigid-as-possible (ARAP) corresponding mesh deformations. We support stretchable-and-twistable bones (STBs) and spines by generalizing the ARAP deformations to stretchable deformers. Additionally, our approach can optimize joint placements. If wanted, a user can guide and interact with the results, which is facilitated by an interactive feedback, reached via an efficient sparsification scheme. We demonstrate our technique on challenging inputs (STBs and spines, triangle and tetrahedral meshes featuring missing elements, boundaries, self-intersections, or wire edges).
Jean-Marc Thiery and Elmar Eisemann
Computer Graphics Forum 2017

We propose a novel framework for photometric stereo (PS) under low-light conditions using uncalibrated near- light illumination. It operates on free-form video sequences captured with a minimalistic and affordable setup. We address issues such as albedo variations, shadowing, perspective projections and camera noise. Our method uses specular spheres detected with a perspective-correcting Hough transform to robustly triangulate light positions in the presence of outliers via a least-squares approach. Furthermore, we propose an iterative reweighting scheme in combination with an l_p-norm minimizer to robustly solve the calibrated near-light PS problem. In contrast to other approaches, our framework reconstructs depth, albedo (relative to light source intensity) and normals simultaneously and is demonstrated on synthetic and real-world scenes.
Jingtang Liao, Bert Buchholz, Jean-Marc Thiery, Pablo Bauszat, and Elmar Eisemann
Transactions on Image Processing 2017

We propose a practical iterative remeshing algorithm for multi-material tetrahedral meshes which is solely based on simple local topological operations, such as edge collapse, flip, split and vertex smoothing. To do so, we exploit an intermediate implicit feature complex which reconstructs piecewise smooth multi-material boundaries made of surface patches, feature edges and corner vertices. Futhermore, we design specific feature-aware local remeshing rules which, combined with a moving least square projection, result in high quality isotropic meshes representing the input mesh at a user defined resolution while preserving important features. Our algorithm uses only topology-aware local operations, which allows to process difficult input meshes such as self-intersecting ones. We evaluate our approach on a collection of examples and experimentally show that it is fast and scales well.
Noura Faraj, Jean-Marc Thiery, and Tamy Boubekeur
Computer & Graphics 2016 - proceedings of Shape Modeling International 2016 - Best paper award

Performance capture systems are used to acquire high-quality animated 3D surfaces, usually in form of a dense 3D triangle mesh. Extracting a more compact, yet faithful representation is often desirable, but existing solutions for animated sequences are surface-based, which leads to a limited approximation power in the case of extreme simplification. We introduce animated sphere-meshes, which are meshes indexing a set of animated spheres. Our solution is the first to output an animated volumetric structure to approximate animated 3D surfaces and optimizes for the sphere approximation, connectivity, and temporal coherence. As a result, our algorithm produces a multi-resolution structure from which a level of simplification can be selected in real-time, preserving a faithful approximation of the input, even at the coarsest levels. We demonstrate the use of animated sphere-meshes for low-cost approximate collision detection. Additionally, we propose a skinning decomposition, which automatically rigs the input mesh to the chosen level of detail. The resulting set of weights are smooth, compress the animation, and enable easy edits.
Jean-Marc Thiery, Emilie Guy, Tamy Boubekeur and Elmar Eisemann
Transactions On Graphics 2016 - presented at Siggraph 2016

Voxel-based approaches are today's standard to encode volume data. Recently, directed acyclic graphs (DAGs) were success- fully used for compressing sparse voxel scenes as well, but they are restricted to a single bit of (geometry) information per voxel. We present a method to compress arbitrary data, such as colors, normals, or reflectance information. By decoupling geometry and voxel data via a novel mapping scheme, we are able to apply the DAG principle to encode the topology, while using a palette-based compression for the voxel attributes, leading to a drastic memory reduction. Our method outperforms existing state-of-the-art techniques and is well-suited for GPU architectures. We achieve real-time performance on commodity hardware for colored scenes with up to 17 hierarchical levels (a 128 K^3 voxel resolution), which are stored fully in core.
Bas Dado, Timothy R. Kol, Pablo Bauszat, Jean-Marc Thiery, Elmar Eisemann
Computer Graphics Forum - proceedings of Eurographics 2016

Mean Shift is a well-known clustering algorithm that has attractive properties such as the ability to find non convex and local clusters even in high dimensional spaces, while remaining relatively insensitive to outliers. However, due to its poor computational performance, real-world applications are limited. In this article, we propose a novel acceleration strategy for the traditional Mean Shift algorithm, along with a two-layers strategy, resulting in a considerable performance increase, while maintaining high cluster quality.We also show how to to find clusters in a streaming environment with bounded memory, in which queries need to be answered at interactive rates, and for which no mean shift-based algorithm currently exists. Our online structure can be updated at very minimal cost and as infrequently as possible, and we show how to detect the time at which this update needs to be performed. Our technique is validated extensively in both static and streaming environments.
Daniel van der Ende, Jean-Marc Thiery and Elmar Eisemann
DATA ANALYTICS 2015, The Fourth International Conference on Data Analytics - Best paper award in session "Big Data"

Surface selection is one of the fundamental cornerstone interaction in shape modeling. In the case of complex models, this task is often tedious for at least two reasons: first the local geometry of a given region may be hard to select manually and needs great accuracy; second the selection process may have to be repeated a large number of times for similar regions requiring similar subsequent editing. We propose SimSelect, a new system for interactive selection on 3D surfaces addressing these two issues. We cope with the accuracy issue by classifying selection in different types namely components, parts and patches for which we independently optimize. Second, we address the repetitivity issue by introducing an expansion process based on shape recognition which automatically retrieves potential selections similar to the user-defined one. As a result, our system provides the user with a compact set of simple interaction primitives leveraging a smooth select-and-edit workflow.
Emilie Guy, Jean-Marc Thiery and Tamy Boubekeur
Computer Graphics Forum - proceedings of Eurographics 2014

The Scale Axis Transform provides a parametric simplification of the Medial Axis of a 3D shape which can be seen as a hierarchical description. However, this powerful shape analysis method has a significant computational cost, requiring several minutes for a single scale on a mesh of few thousands vertices. Moreover, the scale axis can be artificially complexified at large scales, introducing new topological structures in the simplified model. In this paper, we propose a progressive medial axis simplification method inspired from surface optimization techniques which retains the geometric intuition of the scale axis transform. We compute a hierarchy of simplified medial axes by means of successive edge-collapses of the input medial axis. These operations prevent the creation of artificial tunnels that can occur in the original scale axis transform. As a result, our progressive simplification approach allows to compute the complete hierarchy of scales in a few seconds on typical input medial axes. We show how this variation of the scale axis transform impacts the resulting medial structure.
Noura Faraj, Jean-Marc Thiery and Tamy Boubekeur
Siggraph Asia 2013 (technical briefs)

Shape approximation algorithms aim at computing simple geometric descriptions of dense surface meshes. Many such algorithms are based on mesh decimation techniques, generating coarse triangulations while optimizing for a particular metric which models the distance to the original shape. This approximation scheme is very efficient when enough polygons are allowed for the simplified model. However, as coarser approximations are reached, the intrinsic piecewise linear point interpolation which defines the decimated geometry fails at capturing even simple structures. We claim that when reaching such extreme simplification levels, highly instrumental in shape analysis, the approximating representation should explicitly and progressively model the volumetric extent of the original shape. In this paper, we propose Sphere-Meshes, a new shape representation designed for extreme approximations and substituting a sphere interpolation for the classic point interpolation of surface meshes. From a technical point-of-view, we propose a new shape approximation algorithm, generating a sphere-mesh at a prescribed level of detail from a classical polygon mesh. We also introduce a new metric to guide this approximation, the Spherical Quadric Error Metric in R4 , whose minimizer finds the sphere that best approximates a set of tangent planes in the input and which is sensitive to surface orientation, thus distinguishing naturally between the inside and the outside of an object. We evaluate the performance of our algorithm on a collection of models covering a wide range of topological and geometric structures and compare it against alternate methods. Lastly, we propose an application to deformation control where a sphere-mesh hierarchy is used as a convenient rig for altering the input shape interactively. !!! Get c++ code here !!!
Jean-Marc Thiery, Emilie Guy and Tamy Boubekeur
Transactions On Graphics - proceedings of Siggraph Asia 2013

Mean Value Coordinates provide an efficient mechanism for the interpolation of scalar functions defined on orientable domains with non-convex boundary. They present several interesting features, including the simplicity and speed that yield from their closed-form expression. In several applications though, it is desirable to enforce additional constraints involving the partial derivatives of the interpolated function, as done in the case of the Green Coordinates approximation scheme for interactive 3D model deformation. In this paper, we introduce the analytic expressions of the Jacobian and the Hessian of functions interpolated through Mean Value Coordinates. We provide these expressions both for the 2D and 3D case. We also provide a thorough analysis of their degenerate configurations along with accurate approximations of the partial derivatives in these configurations. Extensive numerical experiments show the accuracy of our derivation. In particular, we illustrate the improvements of our formulae over a variety of Finite Difference schemes in terms of precision and usability. We demonstrate the utility of this derivation in several applications, including cage-based implicit 3D model deformations (i.e. Variational MVC deformations). This technique allows for easy and interactive model deformations with sparse positional, rotational and smoothness constraints. Moreover, the cages produced by the algorithm can be directly re-used for further manipulations, which makes our framework directly compatible with existing software supporting Mean Value Coordinates based deformations. !!! Get c++ code here !!!
Jean-Marc Thiery, Julien Tierny and Tamy Boubekeur
The Visual Computer Journal 2013

While 3D surfaces are essentially represented using triangle meshes in the domain of digital geometry, the structures that allow to interact with those are various and adapted to the different geometry processing tasks that are targetted by the user. This thesis presents results on structures of various dimension and various geometrical representations, going from internal structures like analytical curve skeletons for shape modeling, to on-surface structures allowing automatic selection of feature handles for shape deformation, and external control structures known as “cages” offering a high-level representation of animated 3D data stemming from performance capture. Results on spatial functions are also presented, in particular for the Mean-Value Coordinates, for which the analytical formulae of the gradients and the Hessians are provided, and biharmonic functions, for which a finite elements basis is given for the resolution of the biharmonic Laplace problem with mixed Dirichlet/Neumann boundary conditions, as well as their applications to 3D shapes deformation.
Jean-Marc Thiery
PhD Thesis in computer graphics. November 2012

Whole-body anatomically correct high-resolution 3D medical images are instrumental for physical simulations. Unfortunately, only a limited number of acquired datasets are available and the scope of possible applications is limited by the patient's posture. In this paper, we propose an extension of the interactive cage-based deformation pipeline VoxMorph [Faraj2012], for labeled voxel grids allowing to efficiently explore the space of plausible poses while preserving the tissues' internal structure. We propose 3 main contributions to overcome the limitations of this pipeline: (i) we improve its robustness by proposing a deformation diffusion scheme, (ii) we improve its accuracy by proposing a new error-metric for the refinement process of the motion adaptive structure, (iii)~we improve its scalability by proposing an out-of-core implementation. Our method is easy to use for novice users, robust and scales up to 3D images that do not fit in memory, while offering limited distortion and mass loss. We evaluate our approach on postured whole-body segmented images and present an electro-magnetic wave exposure study for human-waves interaction simulations.
Noura Faraj, Jean-Marc Thiery, Isabelle Bloch, Nadège Varsier, Joe Wiart and Tamy Boubekeur
Springer Lecture Notes in Computer Science - proceedings of MICCAI Workshop on Mesh Processing in Medical Image Analysis 2012

We present a new curve skeleton model designed for surface modeling and processing. This skeleton is defined as the geometrical integration of a piecewise harmonic parameterization defined over a disk-cylinder surface decomposition. This decomposition is computed using a progressive Region Graph reduction based on both geometric and topological criteria which can be iteratively optimized to improve region boundaries. The skeleton has an analytical form with regularity inherited from the surface one. Such a form offers well-defined surface-skeleton and skeleton-surface projections. The resulting skeleton satisfies quality criteria which are relevant for skeleton-based modeling and processing. We propose applications that benefit from our skeleton model, including local thickness editing, inset surface creation for shell mapping, as well as a new mid-scale feature preserving smoothing.
Jean-Marc Thiery, Bert Buchholz, Julien Tierny and Tamy Boubekeur
Computer Graphics Forum - proceedings of Pacific Graphics 2012

We present a novel framework for converting animated 3D shape sequences into compact and stable cage-based representations. Given a raw animated sequence with one-to-one point correspondences together with an initial cage embedding, our algorithm automatically generates smoothly varying cage embeddings which faithfully reconstruct the enclosed object deformation. Our technique is fast, automatic, oblivious to the cage coordinate system, provides controllable error and exploits a GPU implementation. At the core of our method, we introduce a new algebraic algorithm based on Maximum Volume Sub-matrices (maxvol) to speed up and stabilize the deformation inversion. We also present a new spectral regularization algorithm that can apply arbitrary regularization terms on selected sub-parts of the inversion spectrum. This step allows to enforce a highly localized cage regularization, guaranteeing its smooth variation along the sequence. We demonstrate the speed, accuracy and robustness of our framework on various synthetic and acquired data sets. The benefits of our approach are illustrated in applications such as animation compression and post-editing.
Jean-Marc Thiery, Julien Tierny and Tamy Boubekeur
Computer Graphics Forum (2012) - presented at Eurographics 2013

We propose VoxMorph, a new interactive freeform deformation tool for high resolution voxel grids. Our system exploits cages for high-level deformation control. We tackle the scalability issue by introducing a new 3-scale deformation algorithm composed of a high quality as-rigid-as possible deformation at coarse scale, a quasi-conformal space deformation at mid-scale and a new deformation-adaptive local linear technique at fine scale. The two first scales are applied interactively on a visualization envelope, while the complete full resolution deformation is computed as a post-process after the interactive session, resulting in a high resolution voxel grid containing the deformed model. We tested our system on various real world datasets and demonstrate that our approach offers a good balance between performance and quality.
Noura Faraj, Jean-Marc Thiery and Tamy Boubekeur
Computer & Graphics Journal - proceedings of Shape Modeling International 2012

Interactive freeform surface deformation methods allow to explore the space of possible shapes using simple control structures. While recent advances in variational editing provide high quality deformations, designing control structures remains a time-consuming manual process. We propose a new automatic control structure generation based on the observation that the most salient visual structures of a surface, such as the one exploited in Line Drawing methods, are tightly linked to the potential deformations it may undergo. Our basic idea is to build control structures from those lines in order to provide users with an automatic set of deformation handles to grab and manipulate, avoiding the tedious task of region selection and handle positioning. The resulting interface inherits view-dependency and adaptivity from line definitions, reduces significantly the modeling session time in a number of scenarii, and remains fully compatible with classical handle-based deformations.
Leila Schemali, Jean-Marc Thiery and Tamy Boubekeur
Eurographics 2012 - Short Paper

Everything you can find here is provided without any warranty. Use it at your convenience and at your own risks.
- Derivatives of mean value coordinates in 2D and in 3D (c++)
- SQEM: a standalone implementation of our Spherical Quadric Error Metric (a.k.a. SQEM) (c++)
- More to come...