Abstract We present Sketch2Growth , an interactive system for generating a family of 3D branching shapes and animating their growth from a single user‐drawn style sketch. The sketch, seen as a 2D idealized representation of the desired shape, is converted into a concise format called the Seed . This representation consists of a Directed Acyclic Graph (DAG) that encodes the recursive branching topology, and a series of Gaussian Mixture Models (GMMs) that capture statistical visual‐style at branching points and in terms of branch curvature. During synthesis, the Seed serves as support for a lightweight, stochastic generator: Branches are recursively expanded by unfolding the DAG and sampling from learned distributions, which maintains the expected correlation between parent and child branches. Further growth and variability of the generated shapes are achieved through similarity‐based looping in the Seed structure (re‐starting from a similar node), stochastic mutations and clamping. Only requiring a light learning process through the GMMs, Sketch2Growth ensures perceptual similarity between the generated shapes and the input style sketch, as validated through a user study. In addition, interactive handles enable users to fake the effect of external forces during growth. As results show, our system allows to easily model and animate the continuous growth of complex branching shapes inspired by trees, plants, corals or anatomical structures.

While precise spectral control can be achieved through sparse convolution, corresponding state of the art noise models are typically too expensive for solid noise. We introduce an alternative, wave-based procedural noise model, fast enough to be used in any dimension. We express the noise in the spectral domain and then apply an inverse Fourier transform (FT), requiring the computation of a multidimensional integral. Our contribution is a novel, efficient way to perform this computation, using a sum of precomputed complex-valued hyperplanar wave-functions, oriented in random directions. We show that using suitable wave profiles and combination operators, our model is able to extend to 3D a number of Gaussian and non-Gaussian noises, including Gabor, by-example and Phasor noises, as well as generate novel cellular noises. Our versatile and controllable solid noise model is very compact, a key feature for complex power spectrum and animated noises. We illustrate this through the design of 2D, 3D, and 3D+t materials using color, transparency and style transfer functions.

In this work, we investigate whether artistic hatching, popular in pen-and-ink sketches, can be consistently perceived as a depth cue. We illustrate our results by presenting PerceptualLift, a modeling system that exploits hatching to create curved 3D shapes from a single sketch. We first describe a perceptual user study conducted across a diverse group of participants, which confirms the relevance of hatches as consistent clues for inferring curvature in the depth direction from a sketch. It enables us to extract geometrical rules that link 2D hatch characteristics, such as their direction, frequency, and magnitude, to the changes of depth in the depicted 3D shape. Built on these rules, we introduce PerceptualLift, a flexible tool to model 3D organic shapes by simply hatching over 2D hand-drawn contour sketches.

We present DepthLight, a method to estimate spatial lighting for photorealistic Visual Effects (VFX) using a single image as input. Previous techniques rely either on estimated or captured light representations that fail to account for localized lighting effects, or use simplified lights that do not fully capture the complexity of the illumination process. DepthLight addresses these limitations by using a single LDR image with a limited field of view (LFOV) as an input to compute an emissive texture mesh around the image (a mesh which generates spatial lighting in the scene), producing a simple and lightweight 3D representation for photorealistic object relighting. First, an LDR panorama is generated around the input image using a photorealistic diffusion-based inpainting technique, conditioned on the input image. An LDR to HDR network then reconstructs the full HDR panorama, while an off-the-shelf depth estimation technique generates a mesh representation to finally build a 3D emissive mesh. This emissive mesh approximates the bidirectional light interactions between the scene and the virtual objects that is used to relight virtual objects placed in the scene. We also exploit this mesh to cast shadows from the virtual objects on the emissive mesh, and add these shadows to the original LDR image. This flexible pipeline can be easily integrated into different VFX production workflows. In our experiments, DepthLight shows that virtual objects are seamlessly integrated into real scenes with a visually plausible estimation of the lighting. We compared our results to the ground truth lighting using Unreal Engine, as well as to state-of-the-art approaches that use pure HDRi lighting techniques (see Figure 1). Finally, we validated our approach conducting a user evaluation over 52 participants as well as a comparison to existing techniques.

Having simple methods of illustration is essential to scientific thinking. To complement the abstract sketches regularly used in cell biology, we propose DynBioSketch, an easy-to-use digital modeling and animation tool, enabling biologists to resort to less simplified representations when necessary without having to call professional artists. DynBioSketch is an interactive sketching system dedicated to the design and communication of biological phenomena at the cellular scale that can be illustrated in a few minutes of animation. Our model integrates 3D modeling, pattern-based design of 3D shape distributions, and sketch-based animation. These elements can be combined to create complex scenarios such as the infection phenomenon on which we focus, allowing a narrative design adapted to communication between researchers or educational applications in biology. Our results, along with a user study conducted with biology researchers, highlight the potential of DynBioSketch in enabling the direct design of dynamic visual summaries that convey relevant information, as shown in our infection case study. By bridging the gap between abstract representations used by experts and more illustrative depictions, DynBioSketch opens a new avenue for communicating biological concepts.

We introduce a novel semi-procedural approach that avoids drawbacks of procedural textures and leverages advantages of data-driven texture synthesis. We split synthesis in two parts: 1) structure synthesis, based on a procedural parametric model and 2) color details synthesis, being data-driven. The procedural model consists of a generic Point Process Texture Basis Function (PPTBF), which extends sparse convolution noises by defining rich convolution kernels. They consist of a window function multiplied with a correlated statistical mixture of Gabor functions, both designed to encapsulate a large span of common spatial stochastic structures, including cells, cracks, grains, scratches, spots, stains, and waves. Parameters can be prescribed automatically by supplying binary structure exemplars. As for noise-based Gaussian textures, the PPTBF is used as stand-alone function, avoiding classification tasks that occur when handling multiple procedural assets. Because the PPTBF is based on a single set of parameters it allows for continuous transitions between different visual structures and an easy control over its visual characteristics. Color is consistently synthesized from the exemplar using a multiscale parallel texture synthesis by numbers, constrained by the PPTBF. The generated textures are parametric, infinite and avoid repetition. The data-driven part is automatic and guarantees strong visual resemblance with inputs.

After a five year R&D program, the veRTIGE project is leading up to a world premiere: Visualising the result of the simulation of galaxy formation (GALMER) in real-time in a planetarium. Using physics calculations rather than an artist’s CG representation allows much more to be explained, by giving access with a single model to different instruments’ views and the internal structure of the represented galaxies.

We present an implementation of the GigaVoxels rendering engine used to render large scenes and detailed objects in real-time. Implemented in CUDA, it leverages the performance and features of massively parallel graphics processors. It is based on a volumetric pre-filtered geometry representation and an associated voxel-based approximate cone tracing that allows a high performance rendering with high quality filtering. The underlying data structure exploits the fact that in CG scenes, details are often concentrated on their interface and shows that volumetric models might become a valuable alternative as a rendering primitive for real-time applications. Our solution is based on an adaptive hierarchical data representation depending on the current view, coupled to a ray-casting rendering algorithm. The core system, a GPU cache mechanism, provides a paging of data in video memory and is coupled with a data production pipeline able to dynamically load or produce voxel data on the GPU. Data production and caching in video memory is based on data requests and usage information emitted during rendering. We illustrate our approach with several applications. We present features provided by the library trough examples taking from our SDK, and show a survey of our programming paradigm.

Nous presentons la librairie GigaVoxels utilisee pour rendre de tres grandes scenes et objets detailles en temps-reel. Implementee en CUDA, elle tire parti des performances et fonctionnalites massivement paralleles des processeurs graphiques. Basee sur une representation geometrique pre-filtree volumique et associee a un algorithme de type cone tracing a base de voxels, elle permet un rendu haute performance avec une grande qualite de filtrage. La structure de donnees sous-jacente, un SVO (Sparse Voxel Octree), exploite le fait que dans les scenes 3D, les details sont souvent concentres sur leur interface et montre que les modeles volumetriques peuvent devenir une alternative interessante en tant que primitive de rendu pour les applications temps-reel. Notre solution est basee sur une representation hierarchique adaptative de donnees en fonction du point de vue en cours, couple a un algorithme de ray-casting. Le coeur du systeme, un mecanisme de cache implemente GPU, offre une pagination des donnees en memoire video et est couple a un pipeline de production de donnees capable de charger dynamiquement ou produire des voxels a la volee sur GPU. La production des donnees et la mise en cache dans la memoire video sont basees sur des requetes de donnees et d'informations d'utilisation emises lors du rendu. Nous illustrons notre approche avec plusieurs applications.