Teaching and PhD defense
Joëlle Thollot and Georges-Pierre Bonneau are both full Professor of Computer Science. They teach general computer science topics at basic and intermediate levels, and advanced courses in computer graphics and visualization at the master levels .
Nicolas Holzschuch teaches computer graphics at intermediate and advanced levels.
PhD of Pierre Bénard
This PhD thesis  deals with non-photorealistic rendering, a sub-field of computer graphics which aims at defining creation and processing tools to stylize images and animations. It has applications in all the fields that need stylized depictions, such as entertainment (e. g., video games, animated films, cartoons), virtual her- itage, technical illustration, etc. Besides quality and expression of style, a crucial criterion to assert the quality of an image is the absence of visual artifacts. While already true for traditional art, this consideration is especially important in computer graphics. Indeed the intrin- sic discrete nature of an image can lead to artifacts. This is even more noticeable during animations, as temporal artifacts are added to spatial ones. Precisely defin- ing these artifacts is complex as certain flaws of a given style may be part of its unique and desirable quality (e. g., the imperfections in a hand-made work). The goal of this thesis is twofold: (1) To analyse and perceptually evaluate these artifacts; (2) To propose new methods for stylizing real-time 3D animations. First we present a set of techniques to ensure the coherence of line drawings ex- tracted form 3D animated scenes. Then we propose two methods to stylize shaded regions, which allow to create a wide variety of patterns. The shared ground layer of all these approaches is the use of temporally varying textures to represent the simulated media (e. g., watercolor pigments, brush strokes). Finally we describe two user studies aiming at evaluating the quality of the results produced by such techniques.
PhD of Cyril Crassin
In this thesis  , we present a new approach to efficiently render large scenes and detailed objects in real- time. Our approach is based on a new volumetric pre-filtered geometry representation and an asso- ciated voxel-based approximate cone tracing that allows an accurate and high performance rendering with high quality filtering of highly detailed geometry. In order to bring this voxel representation as a standard real-time rendering primitive, we propose a new GPU-based approach designed to entirely scale to the rendering of very large volumetric datasets. Our system achieves real-time rendering performance for several billion voxels. Our data structure exploits the fact that in CG scenes, details are often concentrated on the interface between free space and clusters of density and shows that volumetric models might become a valuable alternative as a rendering primitive for real-time applications. In this spirit, we allow a quality/performance trade-off and exploit temporal coherence. Our solution is based on an adaptive hierarchical data representation depending on the current view and occlusion information, coupled to an efficient ray-casting rendering algorithm. We introduce a new GPU cache mechanism providing a very efficient paging of data in video memory and imple- mented as a very efficient data-parallel process. This cache is coupled with a data production pipeline able to dynamically load or produce voxel data directly on the GPU. One key element of our method is to guide data production and caching in video memory directly based on data requests and usage information emitted directly during rendering. We demonstrate our approach with several applications. We also show how our pre-filtered geom- etry model and approximate cone tracing can be used to very efficiently achieve blurry effects and real-time indirect lighting.
PhD of Pierre-Edouard Landes
Processing graphical data, either for its editing or the synthesis of new content, demands a good balance between the different sources of information one may exploit. Unlike "procedural" techniques, synthesis by example stands out thanks to its extreme ease-of-use : indeed, tasks such as identification, analysis and reproduction of the distinguishing features of the user-provided examples are left to the method itself. Such approaches, along with today's intricate editing methods have greatly favored the production of compelling graphical content at a wide scale, and henceforth facilitated the adoption of computer-assisted tools by artists. But in order to meet with success, they also have to be highly controllable without being a mere extension of the artist's hand. We explore here such concerns in the context of expressive rendering and study the interactions, may they be collaborative or competitive, between the different sources of information at the core of such processes. In our opinion, there are three main sources of information: the automatic analysis of the inputs before processing; the use of prior knowledge through predetermined models; and users' explicit intervention. Through a clever combination of these sources, we propose new expressive synthesis techniques which satisfy the aforementioned usability. More than photographic realism, expressive rendering strives for the fulfillment of less easily quantifiable goals such as the intelligibility or the aesthetic value of its results. The subjectivity behind the assessment of such criteria thus forces us to attach much importance to the careful choice of the source of information to favor; the required amount of user intervention (without being detrimental to the method's theoretical value); and the possible resort to prior models (without endangering its generality). Three main synthesis instances are studied in this document  : texture generation, image de-colorization, and artistic line rendering. The great disparity of inputs (raster and vector textures, complex images, 3d meshes), terms of synthesis (imitation, conversion, depiction) and objectives (preservation of a texture's visual signature, plausible restitution of chromatic contrasts, creation of drawings in accordance with users' styles) gives rise to distinct balances between those sources of information and requires the consideration of various modes of user interaction.
PhD of Charles de Rousiers
Reproducing efficiently the appearance of complex materials is a crucial problem in the synthesis of realistic images. These are used involved in the production of video games and movies. Apart from global light transport, the realism of a synthetic image is mostly due to the adequate representation of local light transport, i.e. the interactions between light and matter. Modeling these interactions gives rise to a large variety of reflectance models. We therefore propose a classification of these models based on the scales of their ab- stract geometric details. We present in the thesis  the following contributions :
a transmitting reflectance model for transparent rough surfaces such a frosted glass. The efficiency of our model allows real-time performances,
a study and a model of energy propagation in material composed of dense packed discrete particles,
an alternative basis for representing and lighting efficiently measured mate- rials having a low frequency reflectance.
Our contributions permit the abstraction of local interactions while keeping the realism of fully simulated local light transport models.