Adrien Peytavie

Plant ecosystems are an essential element in bringing virtual worlds to life. However, current modeling methods do not scale well to large virtual environments due to the complexity of the interactions between individual trees required to accurately model realistic plant distributions. The resulting lengthy run-times also hamper authoring. To address the twin demands of scalability and interactive authoring, we introduce a hybrid grid-based simulation that distinguishes between the individual modeling of mature trees, whose interactions are encoded with convolution-like operations, and the aggregate modeling of small trees (encompassing saplings and bushes), which are encoded using a per-cell mean-tree representation. Our simulation model is well-suited to parallelization and operates efficiently on graphics hardware, outperforming existing ecosystem simulation approaches by three orders of magnitude without sacrificing ecological consistency and fundamental emergent phenomena. It also enables a full range of interactive control: artists and designers can directly steer the simulation through a painting interface, tune global ecological or climate parameters on the fly, and immediately observe the impact of their choices, making the system suitable for interactive authoring of virtual ecosystems, at a landscape scale of up to 8 × 8 km ² and 100 million trees (at update rates below 47 ms per simulated year). Much larger ecosystems ( e.g. , 24 × 24 km ² with 975 million trees) can still be simulated in about 413 ms per simulated year.

We introduce the PhaseTree, a novel hierarchical construction-tree representation for compactly modeling volumetric objects composed of multiple phases or materials across scales. An object is defined as a single construction tree that combines phase-aware primitives through composition and warping operators, yielding a unified multiphase signed distance representation that naturally supports complex topologies and interfaces between phases. The PhaseTree is compatible with standard signed distance field workflows: single-phase algorithms can be directly promoted to a PhaseTree, and conversely reduced without loss of information. As a result, our model integrates seamlessly with existing algorithms and rendering pipelines. We extend classical Sphere Tracing to robustly handle multiphase configurations and show that, despite the additional expressiveness, our implementation preserves the compactness and resolution independence of signed distance fields and incurs less than a 25% runtime overhead compared to single-phase Sphere Tracing.

To support the design and subsequent generation of terrestrial planets for use in the creative media, we propose a solution that employs a generative model trained on satellite data from planetary bodies with a defined solid surface, such as the Earth and Mars. A user sketches coarse elevation, landcover, temperature, and precipitation directly onto a globe. Our model then infers high‐resolution heightmap and surface appearance layers at planetary scales, with sufficient detail to enable animated flyovers within the exosphere at a distance of a few thousand kilometers from the planet surface. We address the issue of distortion in the mapping from atlas to globe using a quadsphere representation, and the consistency of large‐scale geomorphological features by extracting a global river network from the sketch inputs and providing this as conditioning to the diffusion. As our results demonstrate, our generative model provides a balance between: authoring control through a multi‐layer painting interface with a satellite image pre‐visualization; computation times proportional to the surface area being generated; landscape diversity, displaying, without repetition artefacts, the full range of elevation and landcover features drawn from multiple source planets, and geomorphological plausibility through the provision of a consistent uninterrupted exorheic global river network, where the input sketches allow.

Digital terrains are central to realistic landscape depiction, yet authoring tools must balance perceptual realism with intuitive artistic control. We propose a compact vector‐based representation that models terrain as nested iso‐contours, inspired by geomorphology and cartography. Our method departs from traditional grid‐based elevation models by generating contours through an inward Open Eden Growth simulation, followed by marching‐triangles reconstruction into a Triangulated Irregular Network. This contour framework supports direct editing such as warping, slope modulation, and smoothing, while allowing reconstruction of a standard elevation map for downstream processing, including erosion and amplification. The approach enables the creation of diverse, realistic terrains from minimal user input and offers simple yet powerful control for designers.

Dans cette thèse, nous abordons le problème de la génération automatique de contenu graphique avec un haut niveau de détails pour la génération de mondes. Dans cette quête du réalisme, les principaux verrous scientifiques et techniques sont : la gestion des masses de données géométriques nécessaires à la création de variétés d'objets naturels, la prise en compte des interactions en les différents objets et le contrôle utilisateur.Notre approche s'appuie sur un modèle volumique original et unificateur permettant de représenter les différents matériaux d'un terrain. Nous proposons un ensemble d'algorithmes de haut niveau, combinant des étapes de simulation pour assurer la plausibilité physique et le réalisme visuel à des techniques de génération procédurale permettant de gérer efficacement la complexité. Nos algorithmes permettent ainsi de sculpter des terrains complexes avec des grottes ou des surplombs et de générer des routes avec des tunnels et des ponts permettant le franchissement d'obstacles naturels.

Processing and particularly visualizing implicit surfaces remains computationally intensive when dealing with complex objects built from construction trees. We introduce optimization nodes to reduce the computational cost of the field function evaluation for hierarchical construction trees, while preserving the Lipschitz or conservative properties of the function. Our goal is to propose acceleration nodes directly embedded in the construction tree, and avoid external, accompanying data‐structures such as octrees. We present proxy and continuous level of detail nodes to reduce the overall evaluation cost, along with a normal warping technique that enhances surface details with negligible computational overhead. Our approach is compatible with existing algorithms that aim at reducing the number of function calls. We validate our methods by computing timings as well as the average cost for traversing the tree and evaluating the signed distance field at a given point in space. Our method speeds‐up signed distance field evaluation by up to three orders or magnitude, and applies both to ray‐surface intersection computation in Sphere Tracing applications, and to polygonization algorithms.

Vector‐based graphics offer numerous advantages over grid‐based models, including resolution independence and ease of manipulation. Despite these benefits, their use in landscape modelling remains uncommon because of a lack of direct editing and interactive feedback, essential for matching the artist's vision. We introduce a new vector‐based model for creating digital terrains based on computationally efficient primitives. We propose a method to convert grid‐based digital elevation maps to this representation with a user‐defined level of accuracy. Once vectorized, the terrain can be authored using interactive high‐level skeleton‐based tools adapted to the primitive representation, allowing local deformations that automatically adapt to underlying geomorphological structures and landforms of the terrain.

Modeling high-resolution terrains is a perennial challenge in the creation of virtual worlds. In this paper, we focus on the amplification of a low-resolution input terrain into a high-resolution, hydrologically consistent terrain featuring complex patterns by a multi-scale approach. Our framework combines the best of both worlds, relying on physics-inspired erosion models producing consistent erosion landmarks and introducing control at different scales, thus bridging the gap between physics-based erosion simulations and multi-scale procedural modeling. The method uses a fast and accurate approximation of different simulations, including thermal, stream power erosion and deposition performed at different scales to obtain a range of effects. Our approach provides landscape designers with tools for amplifying mountain ranges and valleys with consistent details.

Various terrain modelling methods have been proposed for the past decades, providing efficient and often interactive authoring tools. However, they seldom include any notion of style, which is critical for designers in the entertainment industry. We introduce a new generative network method that bridges the gap between automatic terrain synthesis and authoring, providing a versatile set of authoring tools allowing spatialised style. We build upon the StyleGAN2 architecture and extend it with authoring tools. Given an input sketch or existing elevation map, our method generates a terrain with features that can be authored, enhanced, and augmented using interactive brushes and style manipulation tools. The strength of our approach lies in the versatility and interoperability of the different tools. We validate our method quantitatively with drainage calculation against other previous techniques and qualitatively by asking users to follow a prompt or freely create a terrain.