2025Activity reportProject-TeamMAVERICK
RNSR: 201221005J- Research center Inria Centre at Université Grenoble Alpes
- In partnership with:CNRS, Université de Grenoble Alpes
- Team name: Models and Algorithms for Visualization and Rendering
- In collaboration with:Laboratoire Jean Kuntzmann (LJK)
Creation of the Project-Team: 2014 January 01
Each year, Inria research teams publish an Activity Report presenting their work and results over the reporting period. These reports follow a common structure, with some optional sections depending on the specific team. They typically begin by outlining the overall objectives and research programme, including the main research themes, goals, and methodological approaches. They also describe the application domains targeted by the team, highlighting the scientific or societal contexts in which their work is situated.
The reports then present the highlights of the year, covering major scientific achievements, software developments, or teaching contributions. When relevant, they include sections on software, platforms, and open data, detailing the tools developed and how they are shared. A substantial part is dedicated to new results, where scientific contributions are described in detail, often with subsections specifying participants and associated keywords.
Finally, the Activity Report addresses funding, contracts, partnerships, and collaborations at various levels, from industrial agreements to international cooperations. It also covers dissemination and teaching activities, such as participation in scientific events, outreach, and supervision. The document concludes with a presentation of scientific production, including major publications and those produced during the year.
Keywords
Computer Science and Digital Science
- A5.2. Data visualization
- A5.5. Computer graphics
- A5.5.1. Geometrical modeling
- A5.5.2. Rendering
- A5.5.3. Computational photography
- A5.5.4. Animation
Other Research Topics and Application Domains
- B5.5. Materials
- B5.7. 3D printing
- B9.2.2. Cinema, Television
- B9.2.3. Video games
- B9.2.4. Theater
- B9.6.6. Archeology, History
1 Team members, visitors, external collaborators
Research Scientists
- Fabrice Neyret [Team leader, CNRS, Senior Researcher, HDR]
- Nicolas Holzschuch [INRIA, Senior Researcher, On partial secondment to the trade union CFDT Education-Formation Recherche Publiques, HDR]
- Cyril Soler [INRIA, Researcher, HDR]
Faculty Members
- Joelle Thollot [GRENOBLE INP, Professor, half Inria delegation until Aug 2025, HDR]
- Thibault Tricard [GRENOBLE INP, Associate Professor]
- Romain Vergne [UGA, Associate Professor]
PhD Students
- Ambre Adjevi-Neglokpe [UGA]
- Patrick Attimont [UGA, from Oct 2025]
- Mohamed Amine Farhat [UGA, until Jun 2025]
- Pacome Luton [UGA]
- Matheo Moinet [UGA]
- Antoine Richermoz [INRIA, from Oct 2025]
- Antoine Richermoz [UGA, until Sep 2025]
- Ran Yu [OCV Chambéry International, CIFRE]
Interns and Apprentices
- Elodie Arock [GRENOBLE INP, Intern, from May 2025 until Jul 2025]
- Patrick Attimont [UGA, Intern, from Mar 2025 until Aug 2025]
- Felix Clavel [GRENOBLE INP, from May 2025 until Jul 2025]
- Malo Desgagny [UGA, Intern, from May 2025 until Jun 2025]
- Maxence Doktorcik [UGA, Intern, until Jun 2025]
- Aurelie Gillot [UGA, Intern, from Feb 2025 until Aug 2025]
- Hasni Pelletier [UGA, Intern, until Jan 2025]
- Thilen Savignon [INRIA, Intern, from Feb 2025 until Jun 2025]
Administrative Assistant
- Diane Courtiol [INRIA]
External Collaborators
- Nolan Mestres [Auto-entrepreneur]
- Arthur Novat [Atelier Pierre Novat, until Aug 2025]
2 Overall objectives
Computer-generated pictures and videos are now ubiquitous: both for leisure activities, such as special effects in motion pictures, feature movies and video games, or for more “serious” activities, such as visualization and simulation.
Maverick was created as a research team in January 2012 and upgraded as a research project in January 2014. We deal with image synthesis methods. We place ourselves at the end of the image production pipeline, when the pictures are generated and displayed (see Figure 1). We take many possible inputs: datasets, video flows, pictures and photographs, (animated) geometry from a virtual world... We produce as output pictures and videos.
These pictures will be viewed by humans, and we consider this fact as an important point of our research strategy, as it provides the benchmarks for evaluating our results: the pictures and animations produced must be able to convey the message to the viewer. The actual message depends on the specific application: data visualization, exploring virtual worlds, designing paintings and drawings... Our vision is that all these applications share common research problems: ensuring that the important features are perceived, avoiding cluttering or aliasing, efficient internal data representation, etc.
Computer Graphics, and especially Maverick, is at the crossroad between fundamental research and industrial applications. We are both looking at the constraints and needs of applicative users and targeting long term research issues such as sampling and filtering.
Position of the team in the graphics pipeline
The Maverick project-team aims at producing representations and algorithms for efficient, high-quality computer generation of pictures and animations through the study of four research problems:
- Computer Visualization, where we take as input a large localized dataset and represent it in a way that will let an observer understand its key properties.
- Expressive Rendering, where we create an artistic representation of a virtual world.
- Illumination Simulation, where our focus is modelling the interaction of light with the objects in the scene.
- Complex Scenes, where our focus is rendering and modelling highly complex scenes.
The heart of Maverick is understanding what makes a picture useful, powerful and interesting for the user, and designing algorithms to create these pictures.
We will address these research problems through three interconnected approaches:
- working on the impact of pictures, by conducting perceptual studies, measuring and removing artefacts and discontinuities, evaluating the user response to pictures and algorithms.
- developing representations for data, through abstraction, stylization and simplification.
- developing new methods for predicting the properties of a picture (e.g. frequency content, variations) and adapting our image-generation algorithm to these properties.
A fundamental element of the Maverick project-team is that the research problems and the scientific approaches are all cross-connected. Research on the impact of pictures is of interest in three different research problems: Computer Visualization, Expressive rendering and Illumination Simulation. Similarly, our research on Illumination simulation will gather contributions from all three scientific approaches: impact, representations and prediction.
3 Research program
The Maverick project-team aims at producing representations and algorithms for efficient, high-quality computer generation of pictures and animations through the study of four research problems:
- Computer Visualization where we take as input a large localized dataset and represent it in a way that will let an observer understand its key properties. Visualization can be used for data analysis, for the results of a simulation, for medical imaging data...
- Expressive Rendering, where we create an artistic representation of a virtual world. Expressive rendering corresponds to the generation of drawings or paintings of a virtual scene, but also to some areas of computational photography, where the picture is simplified in specific areas to focus the attention.
- Illumination Simulation, where we model the interaction of light with the objects in the scene, resulting in a photorealistic picture of the scene. Research include improving the quality and photorealism of pictures, including more complex effects such as depth-of-field or motion-blur. We are also working on accelerating the computations, both for real-time photorealistic rendering and offline, high-quality rendering.
- Complex Scenes, where we generate, manage, animate and render highly complex scenes, such as natural scenes with forests, rivers and oceans, but also large datasets for visualization. We are especially interested in interactive visualization of complex scenes, with all the associated challenges in terms of processing and memory bandwidth.
The fundamental research interest of Maverick is first, understanding what makes a picture useful, powerful and interesting for the user, and second designing algorithms to create and improve these pictures.
3.1 Research approaches
We will address these research problems through three interconnected research approaches:
Picture Impact
Our first research axis deals with the impact pictures have on the viewer, and how we can improve this impact. Our research here will target:
- evaluating user response: we need to evaluate how the viewers respond to the pictures and animations generated by our algorithms, through user studies, either asking the viewer about what he perceives in a picture or measuring how his body reacts (eye tracking, position tracking).
- removing artefacts and discontinuities: temporal and spatial discontinuities perturb viewer attention, distracting the viewer from the main message. These discontinuities occur during the picture creation process; finding and removing them is a difficult process.
Data Representation
The data we receive as input for picture generation is often unsuitable for interactive high-quality rendering: too many details, no spatial organization... Similarly the pictures we produce or get as input for other algorithms may contain superfluous details.
One of our goals is to develop new data representations, adapted to our requirements for rendering. This includes fast access to the relevant information, but also access to the specific hierarchical level of information needed: we want to organize the data in hierarchical levels, pre-filter it so that sampling at a given level also gives information about the underlying levels. Our research for this axis includes filtering, data abstraction, simplification and stylization.
The input data can be of any kind: geometric data, such as the model of an object, scientific data before visualization, pictures and photographs. It can be time-dependent or not; time-dependent data bring an additional level of challenge on the algorithm for fast updates.
Prediction and simulation
Our algorithms for generating pictures require computations: sampling, integration, simulation... These computations can be optimized if we already know the characteristics of the final picture. Our recent research has shown that it is possible to predict the local characteristics of a picture by studying the phenomena involved: the local complexity, the spatial variations, their orientation...
Our goal is to develop new techniques for predicting the properties of a picture, and to adapt our image-generation algorithms to these properties, for example by sampling less in areas of low variation.
Our research problems and approaches are all cross-connected. Research on the impact of pictures is of interest for three different research problems: Computer Visualization, Expressive rendering and Illumination Simulation. Similarly, our research on Illumination simulation will use all three research approaches: impact, representations and prediction.
3.2 Cross-cutting research issues
Beyond the connections between our problems and research approaches, we are interested in several issues, which are present throughout all our research:
-
Sampling:
is an ubiquitous process occurring in all our application domains, whether photorealistic rendering (e.g. photon mapping), expressive rendering (e.g. brush strokes), texturing, fluid simulation (Lagrangian methods), etc. When sampling and reconstructing a signal for picture generation, we have to ensure both coherence and homogeneity. By coherence, we mean not introducing spatial or temporal discontinuities in the reconstructed signal. By homogeneity, we mean that samples should be placed regularly in space and time. For a time-dependent signal, these requirements are conflicting with each other, opening new areas of research.
-
Filtering:
is another ubiquitous process, occuring in all our application domains, whether in realistic rendering (e.g. for integrating height fields, normals, material properties), expressive rendering (e.g. for simplifying strokes), textures (through non-linearity and discontinuities). It is especially relevant when we are replacing a signal or data with a lower resolution (for hierarchical representation); this involves filtering the data with a reconstruction kernel, representing the transition between levels.
-
Performance and scalability:
are also a common requirement for all our applications. We want our algorithms to be usable, which implies that they can be used on large and complex scenes, placing a great importance on scalability. For some applications, we target interactive and real-time applications, with an update frequency between 10 Hz and 120 Hz.
-
Coherence and continuity:
in space and time is also a common requirement of realistic as well as expressive models which must be ensured despite contradictory requirements. We want to avoid flickering and aliasing.
-
Animation:
our input data is likely to be time-varying (e.g. animated geometry, physical simulation, time-dependent dataset). A common requirement for all our algorithms and data representation is that they must be compatible with animated data (fast updates for data structures, low latency algorithms...).
3.3 Methodology
Our research is guided by several methodological principles:
-
Experimentation:
to find solutions and phenomenological models, we use experimentation, performing statistical measurements of how a system behaves. We then extract a model from the experimental data.
-
Validation:
for each algorithm we develop, we look for experimental validation: measuring the behavior of the algorithm, how it scales, how it improves over the state-of-the-art... We also compare our algorithms to the exact solution. Validation is harder for some of our research domains, but it remains a key principle for us.
-
Reducing the complexity of the problem:
the equations describing certain behaviors in image synthesis can have a large degree of complexity, precluding computations, especially in real time. This is true for physical simulation of fluids, tree growth, illumination simulation... We are looking for emerging phenomena and phenomenological models to describe them (see framed box “Emerging phenomena”). Using these, we simplify the theoretical models in a controlled way, to improve user interaction and accelerate the computations.
-
Transferring ideas from other domains:
Computer Graphics is, by nature, at the interface of many research domains: physics for the behavior of light, applied mathematics for numerical simulation, biology, algorithmics... We import tools from all these domains, and keep looking for new tools and ideas.
-
Develop new fondamental tools:
In situations where specific tools are required for a problem, we will proceed from a theoretical framework to develop them. These tools may in return have applications in other domains, and we are ready to disseminate them.
-
Collaborate with industrial partners:
we have a long experience of collaboration with industrial partners. These collaborations bring us new problems to solve, with short-term or medium-term transfer opportunities. When we cooperate with these partners, we have to find what they need, which can be very different from what they want, their expressed need.
4 Application domains
The natural application domain for our research is the production of digital images, for example for movies and special effects, virtual prototyping, video games... Our research have also been applied to tools for generating and editing images and textures, for example generating textures for maps. Our current application domains are:
- Offline and real-time rendering in movie special effects and video games;
- Virtual prototyping;
- Scientific visualization;
- Content modeling and generation (e.g. generating texture for video games, capturing reflectance properties, etc);
- Image creation and manipulation.
5 Social and environmental responsibility
While research in the Maverick team generaly involves significantly greedy computer hardware (e.g. 1 Tera-flop graphics cards) and heavy computations, the objective of most work in the Maverick team is the improvement of the performance of algorithms or to create new methods to obtain results at a lower computation cost.
6 Highlights of the year
6.1 Awards
Our paper on spectral theory of light transport 3 is the culmination of several years of research and illustrates a fruitful long-term collaboration with University of Edinburgh.
7 Latest software developments, platforms, open data
7.1 Latest software developments
7.1.1 LavaCake
-
Name:
LavaCake
-
Keywords:
Vulkan, 3D, 3D rendering
-
Functional Description:
LavaCake is an Open Source framework that aims to simplify using Vulkan in C++ for rapid prototyping. This framework provides multiple functions to help the manipulation of the usual Vulkan structure such as queue, command buffer, render pass, shader module, and many more.
- URL:
-
Contact:
Thibault Tricard
7.1.2 shaderV3
-
Keywords:
3D, Vulkan, GPU, 3D rendering
-
Functional Description:
ShaderV is an Open Source framework that aims to simplify using Vulkan in C++ for rapid prototyping.
- URL:
-
Contact:
Antoine Richermoz
-
Partner:
LJK
7.1.3 HQR
-
Name:
High Quality Renderer
-
Keywords:
Lighting simulation, Materials, Plug-in
-
Functional Description:
HQR is a global lighting simulation platform. It provides algorithms for handling materials, geometry and light sources, accepting various industry formats by default. It also provides algorithms for solving light transport simulation problems such as photon mapping, metropolis light transport and bidirectional path tracing. Using a plugin system it allows users to implement their own parts, allowing researchers to test new algorithms for specific tasks.
- URL:
-
Contact:
Cyril Soler
-
Participant:
Cyril Soler
7.1.4 libylm
-
Name:
LibYLM
-
Keyword:
Spherical harmonics
-
Functional Description:
This library implements spherical and zonal harmonics. It provides the means to perform decompositions, manipulate spherical harmonic distributions and provides its own viewer to visualize spherical harmonic distributions.
- URL:
-
Contact:
Cyril Soler
7.1.5 iOS_system
-
Keyword:
IOS
-
Functional Description:
From a programmer point of view, iOS behaves almost as a BSD Unix. Most existing OpenSource programs can be compiled and run on iPhones and iPads. One key exception is that there is no way to call another program (system() or fork()/exec()). This library fills the gap, providing an emulation of system() and exec() through dynamic libraries and an emulation of fork() using threads.
While threads can not provide a perfect replacement for fork(), the result is good enough for most usage, and open-source programs can easily be ported to iOS with minimal efforts. Examples of softwares ported using this library include TeX, Python, Lua and llvm/clang.
-
Release Contributions:
This version makes iOS_system available as Swift Packages, making the integration in other projects easier.
- URL:
-
Contact:
Nicolas Holzschuch
7.1.6 Carnets for Jupyter
-
Keywords:
IOS, Python
-
Functional Description:
Jupyter notebooks are a very convenient tool for prototyping, teaching and research. Combining text, code snippets and the result of code execution, they allow users to write down ideas, test them, share them. Jupyter notebooks usually require connection to a distant server, and thus a stable network connection, which is not always possible (e.g. for field trips, or during transport). Carnets runs both the server and the client locally on the iPhone or iPad, allowing users to create, edit and run Jupyter notebooks locally.
- URL:
-
Contact:
Nicolas Holzschuch
7.1.7 a-Shell
-
Keywords:
IOS, Smartphone
-
Functional Description:
a-Shell is a terminal emulator for iOS. It behaves like a Unix terminal and lets the user run commands. All these commands are executed locally, on the iPhone or iPad. Commands available include standard terminal commands (ls, cp, rm, mkdir, tar, nslookup...) but also programming languages such as Python, Lua, C and C++. TeX is also available. Users familiar with Unix tools can run their favorite commands on their mobile device, on the go, without the need for a network connection.
- URL:
-
Contact:
Nicolas Holzschuch
7.1.8 GRATIN
-
Keywords:
GLSL Shaders, Vector graphics, Texture Synthesis
-
Functional Description:
Gratin is a node-based compositing software for creating, manipulating and animating 2D and 3D data. It uses an internal direct acyclic multi-graph and provides an intuitive user interface that allows to quickly design complex prototypes. Gratin has several properties that make it useful for researchers and students. (1) it works in real-time: everything is executed on the GPU, using OpenGL, GLSL and/or Cuda. (2) it is easily programmable: users can directly write GLSL scripts inside the interface, or create new C++ plugins that will be loaded as new nodes in the software. (3) all the parameters can be animated using keyframe curves to generate videos and demos. (4) the system allows to easily exchange nodes, group of nodes or full pipelines between people.
- URL:
-
Contact:
Romain Vergne
-
Participants:
Pascal Barla, Romain Vergne
-
Partner:
UJF
7.2 Open data
We made available the source code and the data required to reproduce the result from our article "Real-time rendering of animated meshless representations" 5 on github.
8 New results
8.1 Real-Time Rendering of Complex Scenes
8.1.1 GigaVoxels 2.0
Participants: Fabrice Neyret, Antoine Richermoz.
During the PhD thesis of Cyril Crassin (2007-11, now at nVidia Research) and after we developed (and distributed) the GigaVoxels platform (gigavoxels.inria.fr) allowing the realtime quality walkthrough in extremely larged and detailled voxel data. It heavily relies on the GPU, with hierarchical data produced and then cached on the fly on demand by the ray-marcher when a new region get visible, or required at a higher resolution. Still, the limited management of concurent tasks at the time, plus the complex treatment of tile borders at rendering and recollection of necessary information to produce new data, induced far from optimal coverage of the full GPU power and many synchronisations CPU side.
Figures
In his PhD, Antoine Richermoz revisit the problem with the availability of new tools: CUDA streams and graphs, Sparse textures, RayTracing Cores + the ability to relaunch tasks from tasks, etc. In particular, we developed a new model exploiting Dynamic Parallelism where ray-rendering tasks can directly launch voxel production tasks at missing tiles, and those re-launch ray-tasks once completed. This allows to almost totally suppress the times of SM starvation that was occuring in the previous model due to synchronisation between globally alterning task, especially at the end of the frame where only small rendering and production tasks are emitted.
This year we focused on the data structure aspect, which has to host our dynamically produced voxels blocks. In particular we studied the properties of the hardware support of virtual textures (hardware Sparse Textures) allowing to manage individually sub-tiles so as to compress empty space and to dynamically load local content on demand. We could see that not only the performances are surprising low – typically for allowing blocks –, slower than software implementation, but also very variable depending on GPU, OS, driver. We then conducted an in-depth bench and comparison with software implementation. The result was published as a techReport 6.
|
|
compared parallelism scheme; compared SMs timelines using our viewer.
8.1.2 Fast rendering of large and detailled procedural world
Participants: Fabrice Neyret, Mathéo Moinet.
Large and detailled scenes potentially requires a huge amount of data to specify, build, store, load to GPU and render. Even the Gigavoxels approach above still requires large storage in GPU memory, and animation would require regenerating the data, invalidating the cache. Oppositely, procedural methods describe objects or scenes as mathematical constructions, requiring zero storage and only high-level specification by the user. In particular, FBM noises such as Perlin noise allows infinite amount of details, and hypertextures allows to enrich SDF-defined shapes in fractal details. But fractal noise is very costly to evaluate, especially with large range of scales. Worse: with 3D ray-marching, each step in depth counts such that empty areas in front and between objects yield prohibitive cost. Sphere marching techniques allow to do large steps to skip the voids when knowing the distance (SDF) to objects, but we don't have an efficient one for FBM, plus this technics still cause uselessly small steps near silhouettes and behind objects.
In his PhD, Mathéo Moinet revisited the previous work on SDF sphere marching to apply it to FBM. Indeed, decomposing the fractal noise of FBM allows to build an implicit hierarchy of bounding volumes of increased complexity and cost. Lazzy evaluation of this structure allows early-stop of the large-to small fractal sum as soon as we can predict 0-density threshold can't be reached, reducing computational cost. Exploiting this broad-to-detailed evaluation additionaly allows for much bigger steps when far from objects, rather than previous overly conservative small steps everywhere. Relying on higher order in Taylor series further improves this, and the gradient allows to not be deceived by silhouette proximity or behind objects. All together, we could get a 12 folds speedup compare to the naive approach (still relying on bounding box). Note that the methods applies on opaque and transparent objects, still or animated. This lead to a CGF paper 2 presented at Eurographics 2025.
|
| Bounding hierarchy allows to both adapt step size and evaluation cost per step. |
|
| Some results of real-time flyover large and detailed procedural scenes. |
|
| Heatmaps showing ray cost with naive vs our method. |
|
Visual summary of our work on bounding hierarchy |
Visual summary of our work on bounding hierarchy
8.1.3 Embeding complex data in rasterizable proxy
Participants: Pacôme Luton, Fabrice Neyret, Thibault Tricard.
In 2025 we published an article 5 in which we proposed a method to render animated meshless shape in real-time using the rasterization pipeline. To do so we embed our meshless shapes into tetrahedral cage , we animate the tetrahedral cage using linear blend skinning (a traditional approcha for animating geometry), then we render the tetrahedons using our previous work 9 while propagating the animation of the vertices to the mehsless shape. This allows for realtime rendering of animated shape that can be arbitrarily complex. In our article, we demonstrate this by animating Signed Distance Fields (SDF), Voxels, and a mix of both representation, within the rasterization pipeline in real time (more than 60 frames per second). This paper was presented at High-Performance Graphics 2025.
Left to right: Voxel model in rest pose space. Tetrahedral cage animated with linear blend skinning. Voxel model implicitly animated using our method (3.2 ms at 19201080). Complex SDF animated by our method (13.8 ms - see supplementary video). For visualization purposes, we use coarse voxels and tetrahedra.
8.2 Light Transport Simulation
8.2.1 Spectral Theory of Light Transport Operators
Participants: Cyril Soler, Patrick Attimont.
As a sensible follow up to our 2022 Siggraph paper on the compactess of light transport operators we investigated the structure of the spectrum of these operators as well as links between their eigenelements and paths integrals. While compact operators usually have a simple spectrum, non compact ones may show any kind of structure. We published a paper at ACM Transactions on Graphics (TOG) 3 that establishes very original results, taking inspiration from the theory of non self-adjoint operators, the operator formulation of light transport, and Monte-Carlo methods for linear operations on large matrices. This work was done during a long-term collaboration with University of Edinburgh (K.Subr). On Figure 6 below we show eigenvalues and eigenfunctions of the local reflectance operator for various materials.
Figure showing the eigenfunctions of a 3 different materials from the MERL database.
We're currently pursuing our investigations on this topic (A PhD was started in sept. 2025 by P.Attimont). In particular we're interested into developping new methods for solving light transport equations that would not be using Neumann series thereby openning the way to more general light transport problems such as those involved in the calculation of the resolvent of the light transport operator.
8.2.2 Practical models for the reflectance properties of fiber materials
Participants: Ran Yu, Cyril Soler.
Mme Ran Yu is on second year of her Cifre PhD in collaboration with Owens Corning (Chambéry). She is working on the modeling of the reflectance of nonwoven fiber materials.
Her work involves measuring and predicting the properties of complex materials made of intricate glass fiber layers, through multiple approaches including explicit calculation using path tracing, with the purpose of developing new statistical and empirical models of reflectance on these materials.
We're currently working on a future publication that compares BRDF reconstruction methods for converting goniometer-based measurements into full spherical functions. Figure 7 below shows such measured data with linear interpolation.
This image depicts eigenfunctions of the reflectance operator for different materials of the MERL (Misubishi Electric Reflectance Library) database.
8.3 Expressive rendering
8.3.1 micmap project
Participants: Nolan Mestre, Arthur Novat, Romain Vergne, Joëlle Thollot.
micmap is a startup creation project following Nolan Mestres Ph.D. thesis and a long-standing informal collaboration with Arthur Novat (Atelier Novat). This project has won the out of labs challenge (SATT Linksium) in 2021. It has then been funded by the SATT from October 2022 to May 2023 and has been funded by Inria Startup Studio starting from June 1st, 2023 to May 2024. micmap also reveived a BPI France BFTlabs fund of 120k€ in 2024 and a PUI fit'innov grant of 60k€ in 2025.
The micmap team is composed of 3 Maverick members (Nolan Mestres, Joelle Thollot, and Romain Vergne) and 2 external collaborators (Yann Boulanger and Arthur Novat). The goal of the project is to create stylized panorama maps (Figure 8) for tourist agencies, mountain operators, and local authorities.
The project is currently in its maturation phase, combining R&D, market, and economy studies. The goal is to create the company in March 2026 as a SCOP (cooperative society).
Ski map of les portes du Mont-Blanc - ©micmap 2025.
8.3.2 Controllable motion lines generation for an abstracted depiction of 3D motion
Participants: Amine Farhat, Alexandre Bleron, Romain Vergne, Joëlle Thollot.
Motion lines are an essential tool in illustration and animation for conveying and enhancing the perceived movement of an object. In this paper, we propose a user-guided method to generate such lines on top of a rendered 3D scene. Our method is flexible enough to accommodate a variety of line styles, and allows the depiction of complex composite movements in an intuitive way, by granting the user the ability to portray individual motion components using separate sets of lines, as is often done in traditional animation.
Our method takes as input the rendered 3D object and its movement, represented as a hierarchy of transforms varying over time. Users specify a subset of those transforms which represents the movement to be depicted, and an anchor point on the object to guide the placement of the lines. From this, our algorithm generates a 3D "ribbon", a parametrized swept surface evolving over time which acts as a support for rendering motion effects which are coherent with the movement selected by the user. We show how this ribbon and its parametrization can then be used to draw motion lines with controllable lengths, placement, density, and appearance (see Figure 9).
This work has been published in Computers and Graphics'2025 1 and Amine Farhat defended his PhD in July 2025.
Controllable motion lines generation for an abstracted depiction of 3D motion.
9 Bilateral contracts and grants with industry
9.1 Bilateral contracts with industry
Participants: Joëlle Thollot, Romain Vergne, Cyril Soler.
- We have a contract with LeftAngle, connected with the PhD thesis of Amine Farhat (CIFRE).
- We have a contract with Owens Corning France, connected with the PhD thesis of Ran Yu (CIFRE).
10 Partnerships and cooperations
10.1 National initiatives
10.1.1 CDTools: Patrimalp
Participants: Nicolas Holzschuch [contact], Romain Vergne.
The cross-disciplinary project Patrimalp (2018-2022) on Cultural Heritage was extended by Univ. Grenoble-Alpes under the new funding “Cross-Disciplinary Tools”, for a period of 36 months (2023-2026).
The main objective and challenge of the CDTools Patrimalp is to develop a cross-disciplinary approach in order to get a better knowledge of the material cultural heritage in order to ensure its sustainability, valorization and diffusion in society. Carried out by members of UGA laboratories, combining skills in human sciences, geosciences, digital engineering, material sciences, in close connection with stakeholders of heritage and cultural life, curators and restorers, the CDTools Patrimalp intends to develop of a new interdisciplinary science: Cultural Heritage Science.
10.1.2 Collaboration with University of Edinburgh
Participants: Cyril Soler [contact].
As a follow up of the work conducted during the ANR CaLiTrOp that finished in 2022, we have pursuit the spectral analysis of light transport in collaboration with Pr. Kartic Subr at Univ. of Edinburgh. Pr.Subr was invited for a few days in Grenoble and gave a seminar in october 2023. Cyril Soler was invited in Edinburgh in june 2023.
11 Dissemination
11.1 Promoting scientific activities
Participants: Nicolas Holzschuch, Fabrice Neyret, Cyril Soler, Joëlle Thollot, Thibault Tricard, Romain Vergne.
11.1.1 Scientific events: selection
Member of the conference program committees
- Nicolas Holzschuch: Eurographics Symposium on Rendering, 2025.
- Thibault Tricard : Evaluation Committee of the Graphics Replicability Stamp Initiative
Reviewer
Maverick faculties are regular reviewers of most of the major journals and conferences of the domain.
11.1.2 Journal
Reviewer - reviewing activities
Maverick faculties are regular reviewers of most of the major journals and conferences of the domain.
11.1.3 Research administration
- Nicolas Holzschuch is an elected member of the Conseil National de l'Enseignement Supérieur et de la Recherche (CNESER) (2019-2027).
- Nicolas Holzschuch is a member of the Habilitation committee of the École Doctorale MSTII of Univ. Grenoble Alpes.
11.2 Teaching - Supervision - Juries - Educational and pedagogical outreach
11.2.1 Teaching
Participants: Nicolas Holzschuch, Joëlle Thollot, Thibault Tricard, Romain Vergne.
Joëlle Thollot is full Professor of Computer Science. Romain Vergne and Thibault Tricard are both Associate Professor in Computer Science. They teach general computer science topics at basic and intermediate levels, and advanced courses in computer graphics, visualization and artifical intelligence at the master levels. Romain Vergne was in full time délégation Inria until August 2025. Nicolas Holzschuch teaches advanced courses in computer graphics at the master level. Thibault Tricard supervise the "Informatique visuelle" pedagogic team.
- Master: Joëlle Thollot, projet IA, 33h, M2, ENSIMAG, France
- Master: Joëlle Thollot, management, 18h, M1, ENSIMAG, France
- Master : Joelle Thollot, English courses using theater, 18h, M1, ENSIMAG, France.
- Licence : Romain Vergne, Programmation fontionelle, 40h, L1, UGA, France.
- Licence : Romain Vergne, Introduction aux algorithmes, 64h, L1, UGA, France.
- Master : Romain Vergne, Programmation Web, 40h, M2CCI, UGA, France.
- Master : Romain Vergne, Synthèse d'images, 27h, M1, UGA, France.
- Master : Romain Vergne, 3D graphics, 15h, M1, UGA, France.
- Master : Nicolas Holzschuch, Computer Graphics II, 18h, M2 MoSIG, France.
- Master : Nicolas Holzschuch, Synthèse d’Images et Animation, 32h, M2, ENSIMAG, France.
- Master : Thibault Tricard, AI Project 38h, ENSIMAG, France.
- Master : Thibault Tricard, Programmation orienté objet 36h, ENSIMAG, M1, France.
- Master : Thibault Tricard, Graphique 3D, ENSIMAG, M1, 56h, France.
- Master : Thibault Tricard, Synthèse d'images, M1, UGA, 56h, France.
- Master : Thibault Tricard, 3D Graphics, M1, UGA, 35h, France.
- Master : Thibault Tricard, Introduction à l'IA, M1, ENSIMAG, 10h, France.
11.2.2 Supervision
Participants: Fabrice Neyret, Cyril Soler, Joëlle Thollot, Thibault Tricard, Romain Vergne.
- Romain Vergne and Joëlle Thollot co-supervise the PhD of Amine Farhat.
- Thibault Tricard, Romain Vergne and Joëlle Thollot co-supervise the PhD of Ambre Adjevi-Neglokpe.
- Thibault Tricard, and Fabrice Neyret co-supervise the PhD of Pacôme Luton.
- Fabrice Neyret supervises the PhD of Antoine Richermoz.
- Fabrice Neyret supervises the PhD of Matheo Moinet.
- Cyril Soler supervises the PhD of Ran Yu.
- Cyril Soler supervises the PhD of Patrick Attimont.
11.3 Popularization
11.3.1 Participation in Live events
Participants: Fabrice Neyret, Antoine Richermoz, Pacôme Lutton.
- During Fête de la Science, Fabrice Neyret, Antoine Richermoz and Pacôme Luton animated a stand at "la Casemate" (Territoire de Science - Grenoble) about "how computers (and humains) count" (short version + notice).
- During Fête de la Science, Fabrice Neyret, Antoine Richermoz and Pacôme Luton animated 4 high-school 45' classes about "how computers (and humains) count" (long version + notice).
11.3.2 Others science outreach relevant activities
Participants: Fabrice Neyret.
- Fabrice Neyret maintains the blog Shadertoy-Unofficial and various shaders examples on Shadertoy site to popularize GPU technologies as well as disseminates academic models within computer graphics, computer science, applied math and physics fields. About 28k pages viewed and 13k unique visitors (93% out of France) in 2023.
- Fabrice Neyret maintains the blog desmosGraph-Unofficial to popularize the use of interactive grapher DesmosGraph for research, communication and pedagogy. For this year, about 17k pages viewed and 11k unique visitors (99% out of France) in 2023.
- Fabrice Neyret maintains the the blog chiffres-et-paradoxes (in French) to popularize common errors, misunderstandings and paradoxes about statistics and numerical reasoning. About 17k pages viewed and 9k unique visitors since then (15% out of France, knowing the blog is in French) on the blog, plus the viewers via the Facebook and Twitter pages.
12 Scientific production
12.2 Publications of the year
International journals
International peer-reviewed conferences
Reports & preprints
Other scientific publications
12.3 Cited publications
- 9 articleInterval Shading: using Mesh Shaders to generate shading intervals for volume rendering.Proceedings of the ACM on Computer Graphics and Interactive Techniques73April 2024, 1-11HALDOIback to text