This paper presents a novel method, called Deformable Polygonal Flow Matching (DPFM), for the generation of polygonal arrangements such as jigsaw puzzles and floor plans. DPFM is a Flow Matching framework that enables the generation process to deform, rotate, and translate polygons while decoupling these transformations, allowing to toggle them individually. Able to combine the spatial reasoning capabilities of arrangement models with the flexibility of position-based models, it covers a wide range of applications within a unified formulation, from noiseless puzzle solving using rigid alignments to unconstrained floor plan generation.We represent data using a hierarchical graph composed of a topological subgraph encoding connectivity information and semantics (such as room types for floor plans), and a geometrical subgraph encoding the 1D polygonal loop of each shape. DPFM also leverages Flow Matching's arbitrary prior distributions for geometric constraints by designing priors with domain knowledge. Rather than starting the generation process from uninformed distributions, the generation is constrained through the informed priors at the initialization stage. The qualitative and quantitative evaluations of our method, ran on the RPLAN and jigsaw puzzle datasets, demonstrate strong performance. DPFM outperforms task-specific methods, becoming the new state-of-the-art for 2D arrangement generation. Our results show that DPFM is able to solve novel tasks, such as puzzle denoising, where pieces are reconstructed from noisy versions and arranged into a valid puzzle in parallel.

Skeleton-based implicit surfaces, and convolution surfaces in particular, offer an intuitive and expressive representation for geometric modeling. However, their evaluation and rendering remain computationally demanding, and are often affected by aliasing artifacts. In this paper, we introduce a continuous level of detail framework for the automatic simplification of SCALIS convolution surfaces, achieving up to an order-of-magnitude reduction in rendering time while mitigating aliasing artifacts. Our solution dynamically adapts the blending behavior between shape components to preserve the perceived visual appearance of the surface, while progressively simplifying the underlying skeletal geometry. In contrast to traditional simplification techniques, our method allows controlled changes in topological genus when visually beneficial. Our results demonstrate that the proposed framework effectively reduces visual artifacts and computational cost, while maintaining high fidelity to the overall shape.

Abstract 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.

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.

We propose MIRRORED-Anims, a novel retargeting procedure for transferring motion between skinned humanoid characters of different morphologies. It is designed so as to mimic the strengths of the closed-source Mixamo’s retargeting method, currently used as a standard to create motion databases and train all state-of-the-art learning-based retargeting methods, despite severe shortcomings (namely, a lack of character diversity and notable penetration artifacts). Taking inspiration from the toolsets of 3D animators, our retargeting algorithm relies on the control rigs used to manipulate skinned characters, by identifying and transferring controller values on predefined bone mechanisms. While producing motions which are closer to Mixamo’s ground truth than any state-of-the-art learning-based technique, MIRRORED-Anims creates fewer penetration artifacts than observed in the Mixamo dataset, improving the perceived quality of the output. Moreover, motion can be retargeted in real-time to and from the SMPL body model, making it possible to leverage the large motion databases available in SMPL format for the retargeting task. Because it relies solely on transparent, explainable rig operations, MIRRORED-Anims can be used to generate ground-truth motions for any humanoid character, providing a reliable baseline for the future training of learning-based methods. Project page: https://mirrored-anims.github.io/MIRRORED-Anims

We introduce RibbonSculpt, the first method for interactive freeform shape design in VR through progressive sketching of sparse, oriented ribbons. Instead of reconstructing a surface from a fully drawn VR sketch, our method allows the real-time creation and progressive refinement of a closed surface of any topological genus, thanks to the continuous update of a volumetric proxy. The latter corresponds to a filtered subset of the Voronoi balls defined by the user-sketched ribbons. At each visualization step, a mesh extracted from the proxy is beautified through Laplacian-based energy minimization, yielding a smooth surface that interpolates the ribbons. Guided by this surface, users can easily refine their design by adding or removing ribbons, which sculpts, in return, the set of Voronoi balls forming the proxy. Our results, supported by user studies, show that RibbonSculpt allows VR users to easily and quickly draft the 3D shapes they have in mind.

We present an approach for training “agile” character control policies, able to produce a wide variety of motor skills from a single reference motion cycle. Our technique builds off of generative adversarial imitation learning (GAIL), with a key novelty of our approach being to provide modification to the observation map in order to improve agility and robustness. Namely, to support more agile behavior, we adjust the value measurements of the training discriminator through relative features - hence the name ReGAIL. Our state observations include both task relevant relative velocities and poses, as well as relative goal deviation information. In addition, to increase robustness of the resulting gaits, servo gains and damping values are included as part of the policy action to let the controller learn how to best combine tension and relaxation during motion. From a policy informed by a single reference motion, our resulting agent is able to maneuver as needed, at runtime, from walking forward to walking backward or sideways, turning and stepping nimbly. Moreover, thanks to the use of observations in relative frames, the trained controllers are robust to morphological changes of the simulated character, which makes adaptation to new morphologies straightforward. We demonstrate our approach for a humanoid and a quadruped, on both flat and sloped terrains, as well as provide ablation studies to validate the design choices of our framework. In addition, we present an application to prehistoric research, where being able to simulate hominids of specific morphologies on rough terrain is valuable with encouraging results.

Abstract Our goal is to generate realistic human motion from natural language. Modern methods often face a trade‐off between model expressiveness and text‐to‐motion (T2M) alignment. Some align text and motion latent spaces but sacrifice expressiveness; others rely on diffusion models producing impressive motions but lacking semantic meaning in their latent space. This may compromise realism, diversity and applicability. Here, we address this by combining latent diffusion with a realignment mechanism, producing a novel, semantically structured space that encodes the semantics of language. Leveraging this capability, we introduce the task of textual motion inversion to capture novel motion concepts from a few examples. For motion synthesis, we evaluate LEAD on HumanML3D and KIT‐ML and show comparable performance to the state‐of‐the‐art in terms of realism, diversity and text‐motion consistency. Our qualitative analysis and user study reveal that our synthesised motions are sharper, more human‐like and comply better with the text compared to modern methods. For motion textual inversion (MTI), our method demonstrates improvements in capturing out‐of‐distribution characteristics in comparison to traditional VAEs.

Abstract Preserving semantics, in particular in terms of contacts, is a key challenge when retargeting motion between characters of different morphologies. Our solution relies on a low‐dimensional embedding of the character's mesh, based on rigged key vertices that are automatically transferred from the source to the target. Motion descriptors are extracted from the trajectories of these key vertices, providing an embedding that contains combined semantic information about both shape and pose. A novel, adaptive algorithm is then used to automatically select and weight the most relevant features over time, enabling us to efficiently optimize the target motion until it conforms to these constraints, so as to preserve the semantics of the source motion. Our solution allows extensions to several novel use‐cases where morphology and mesh contacts were previously overlooked, such as multi‐character retargeting and motion transfer on uneven terrains. As our results show, our method is able to achieve real‐time retargeting onto a wide variety of characters. Extensive experiments and comparison with state‐of‐the‐art methods using several relevant metrics demonstrate improved results, both in terms of motion smoothness and contact accuracy.

Abstract We present a method for animating herds that automatically tunes a microscopic herd model based on a short video clip of real animals. Our method handles videos with dense herds, where individual animal motion cannot be separated out. Our contribution is a novel framework for extracting macroscopic herd behaviour from such video clips, and then deriving the microscopic agent parameters that best match this behaviour. To support this learning process, we extend standard agent models to provide a separation between leaders and followers, better match the occlusion and field‐of‐view limitations of real animals, support differentiable parameter optimization and improve authoring control. We validate the method by showing that once optimized, the social force and perception parameters of the resulting herd model are accurate enough to predict subsequent frames in the video, even for macroscopic properties not directly incorporated in the optimization process. Furthermore, the extracted herding characteristics can be applied to any terrain with a palette and region‐painting approach that generalizes to different herd sizes and leader trajectories. This enables the authoring of herd animations in new environments while preserving learned behaviour.

Abstract Although intuitive, sketching a closed 3D shape directly in an immersive environment results in an unordered set of arbitrary strokes, which can be difficult to assemble into a closed surface. We tackle this challenge by introducing VRSurf, a surfacing method inspired by a balloon inflation metaphor: Seeded in the sparse scaffold formed by the strokes, a smooth, closed surface is inflated to progressively interpolate the input strokes, sampled into lists of points. These are treated in a divide‐and‐conquer manner, which allows for automatically triggering some additional balloon inflation followed byfusion ifthe current inflation stops due to a detected concavity. While the input strokes are intended to belong to the same smooth 3D shape, our method is robust to coarse VR input and does not require strokes to be aligned. We simply avoid intersecting strokes that might give an inconsistent surface position due to the roughness of the VR drawing. Moreover, no additional topological information is required, and all the user needs to do is specify the initial seeding location for the first balloon. The results show that VRsurf can efficiently generate smooth surfaces that interpolate sparse sets of unoriented strokes. Validation includes a side‐by‐side comparison with other reconstruction methods on the same input VR sketch. We also check that our solution matches the user's intent by applying it to strokes that were sketched on an existing 3D shape and comparing what we get to the original one.

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.

We introduce Arenite, a novel physics-based approach for modeling sandstone structures. The key insight of our work is that simulating a combination of stress and multi-factor erosion enables the generation of a wide variety of sandstone structures observed in nature. We isolate the key shape-forming phenomena: multi-physics fabric interlocking, wind and fluvial erosion, and particle-based deposition processes. Complex 3D structures such as arches, alcoves, hoodoos, or buttes can be achieved by creating simple 3D structures with user-painted erodable areas and vegetation and running the simulation. We demonstrate the algorithm on a wide variety of structures, and our GPU-based implementation achieves the simulation in less than 5 minutes on a desktop computer for our most complex example.

We present an approach for training "agile" character control policies, able to produce a wide variety of motor skills from a single reference motion cycle. Our technique builds off of generative adversarial imitation learning (GAIL), with a key novelty of our approach being to provide modification to the observation map in order to improve agility and robustness. Namely, to support more agile behavior, we adjust the value measurements of the training discriminator through relative features - hence the name ReGAIL. Our state observations include both task relevant relative velocities and poses, as well as relative goal deviation information. In addition, to increase robustness of the resulting gaits, servo gains and damping values are included as part of the policy action to let the controller learn how to best combine tension and relaxation during motion. From a policy informed by a single reference motion, our resulting agent is able to maneuver as needed, at runtime, from walking forward to walking backward or sideways, turning and stepping nimbly. We demonstrate our approach for a humanoid and a quadruped, on both flat and sloped terrains, as well as provide ablation studies to validate the design choices of our framework.

We propose a simple method for the intuitive authoring and efficient animation of virtual tornadoes. Users control the tornado kinematics by sketching two types of curves to specify the initial geometry of the tornado’s core and the profile of the surrounding swirling air, known as the funnel. The first input, a 3D curve, initializes the core as a vortex filament. This filament induces a swirl flow and advects according to its initial curvature, resulting in progressive bending and twisting. The second input consists of one or multiple 2D profile curves that parameterize the Stokes stream function, governing the radial and axial motion of the air around the core and thereby dictate the funnel shape over time. The core and funnel profile are coupled in local frames through closed-form velocities, which together describe the rotation, sliding and uplift within the tornado’s air volume. As shown in our case studies, our method provides a controllable and efficient way to animate visually plausible tornadoes capable of tearing off infrastructure and transporting debris, as well as interacting with uneven terrain.

Abstract We propose an automatic method for generating flight summaries of prescribed duration, given any planed 3D trajectory of a flying object. The challenge is to select relevant time‐ellipses, while keeping and adequately framing the most interesting parts of the trajectory, and enforcing cinematographic rules between the selected shots. Our solution optimizes the visual quality of the output video both in terms of camera view and film editing choices, thanks to a new optimization technique, designed to jointly optimize the selection of the interesting parts of a flight, and the camera animation parameters over time. To our best knowledge, this solution is the first one to address camera control, film editing, and trajectory summarizing at once. Ablation studies demonstrate the visual quality of the flights summaries we generate compared to alternative methods.

Abstract Animating gaze behavior is crucial for creating believable virtual characters, providing insights into their perception and interaction with the environment. In this paper, we present an efficient yet natural‐looking gaze animation model applicable to real‐time walking characters exploring natural environments. We address the challenge of dynamic gaze adaptation by combining findings from neuroscience with a data‐driven saliency model. Specifically, our model determines gaze focus by considering the character's locomotion, environment stimuli, and terrain conditions. Our model is compatible with both automatic navigation through pre‐defined character trajectories and user‐guided interactive locomotion, and can be configured according to the desired degree of visual exploration of the environment. Our perceptual evaluation shows that our solution significantly improves the state‐of‐the‐art saliency‐based gaze animation with respect to the character's apparent awareness of the environment, the naturalness of the motion, and the elements to which it pays attention.

Abstract Explosive volcanic eruptions rank among the most terrifying natural phenomena, and are thus frequently depicted in films, games, and other media, usually with a bespoke once‐off solution. In this paper, we introduce the first general‐purpose model for bi‐directional interaction between the atmosphere and a volcano plume. In line with recent interactive volcano models, we approximate the plume dynamics with Lagrangian disks and spheres and the atmosphere with sparse layers of 2D Eulerian grids, enabling us to focus on the transfer of physical quantities such as temperature, ash, moisture, and wind velocity between these sub‐models. We subsequently generate volumetric animations by noise‐based procedural upsampling keyed to aspects of advection, convection, moisture, and ash content to generate a fully‐realized volcanic skyscape. Our model captures most of the visually salient features emerging from volcano‐sky interaction, such as windswept plumes, enmeshed cap, bell and skirt clouds, shockwave effects, ash rain, and sheathes of lightning visible in the dark.

Abstract While the past of terrain cannot be known precisely because an effect can result from many different causes, exploring these possible pasts opens the way to numerous applications ranging from movies and games to paleogeography. We introduce unerosion, an attempt to recover plausible past topographies from an input terrain represented as a height field. Our solution relies on novel algorithms for the backward simulation of different processes: fluvial erosion, sedimentation, and thermal erosion. This is achieved by re‐formulating the equations of erosion and sedimentation so that they can be simulated back in time. These algorithms can be combined to account for a succession of climate changes backward in time, while the possible ambiguities provide editing options to the user. Results show that our solution can approximately reverse different types of erosion while enabling users to explore a variety of alternative pasts. Using a chronology of climatic periods to inform us about the main erosion phenomena, we also went back in time using real measured terrain data. We checked the consistency with geological findings, namely the height of river beds hundreds of thousands of years ago.

While data is vital to better understand and model interactions within human crowds, capturing real crowd motions is extremely challenging. Virtual Reality (VR) demonstrated its potential to help, by immersing users into either simulated virtual crowds based on autonomous agents, or within motion-capture-based crowds. In the latter case, users' own captured motion can be used to progressively extend the size of the crowd, a paradigm called Record-and-Replay (2R). However, both approaches demonstrated several limitations which impact the quality of the acquired crowd data. In this paper, we propose the new concept of contextual crowds to leverage both crowd simulation and the 2R paradigm towards more consistent crowd data. We evaluate two different strategies to implement it, namely a Replace-Record-Replay (3R) paradigm where users are initially immersed into a simulated crowd whose agents are successively replaced by the user's captured-data, and a Replace-Record-Replay-Responsive (4R) paradigm where the pre-recorded agents are additionally endowed with responsive capabilities. These two paradigms are evaluated through two real-world-based scenarios replicated in VR. Our results suggest that the behaviors observed in VR users with surrounding agents from the beginning of the recording process are made much more natural, enabling 3R or 4R paradigms to improve the consistency of captured crowd datasets.

Abstract Human and animal presence in natural landscapes is initially revealed by the immediate impact of their locomotion, from footprints to crushed grass. In this work, we present an approach to model the effects of virtual characters on natural terrains, focusing on the impact of human locomotion. We introduce a lightweight solution to compute accurate foot placement on uneven ground and infer dynamic foot pressure from kinematic animation data and the mass of the character. A ground and vegetation model enables us to effectively simulate the local impact of locomotion on soft soils and plants over time, resulting in the formation of visible paths. As our results show, we can parameterize various soil materials and vegetation types validated with real-world data. Our method can be used to significantly increase the realism of populated natural landscapes and the sense of presence in virtual applications and games.

Crowd simulation is important for video-games design, since it enables to populate virtual worlds with autonomous avatars that navigate in a human-like manner. Reinforcement learning has shown great potential in simulating virtual crowds, but the design of the reward function is critical to achieving effective and efficient results. In this work, we explore the design of reward functions for reinforcement learning-based crowd simulation. We provide theoretical insights on the validity of certain reward functions according to their analytical properties, and evaluate them empirically using a range of scenarios, using the energy efficiency as the metric. Our experiments show that directly minimizing the energy usage is a viable strategy as long as it is paired with an appropriately scaled guiding potential, and enable us to study the impact of the different reward components on the behavior of the simulated crowd. Our findings can inform the development of new crowd simulation techniques, and contribute to the wider study of human-like navigation.

We introduce the first solution for simulating the formation and evolution of glaciers, together with their attendant erosive effects, for periods covering the combination of glacial and inter-glacial cycles. Our efficient solution includes both a fast yet accurate deep learning-based estimation of highorder ice flows and a new, multi-scale advection scheme enabling us to account for the distinct time scales at which glaciers reach equilibrium compared to eroding the terrain. We combine the resulting glacial erosion model with finer-scale erosive phenomena to account for the transport of debris flowing from cliffs. This enables us to model the formation of terrain shapes not previously adequately modeled in Computer Graphics, ranging from U-shaped and hanging valleys to fjords and glacial lakes.

Structured 2D patterns formed by the anisotropic distribution of arbitrary shapes are ubiquitous in nature and man-made environments. They may include both bounded and unbounded (extended fiber-like) shapes. In this work, we address the problem of interactively generating such patterns from a single exemplar sketched by a user. We build our solution on a new data structure, the Support Structure Hierarchy, computed from a multi-resolution analysis of the input exemplar, that encodes the main anisotropy directions at different scales as well as deviations from them. We propose an efficient method based on this structure to synthesize a similar distribution of shapes in an extended 2D domain. The user can also choose to hybridize multiple input exemplars by combining structural shapes extracted at different scales. As shown in a user study, our multi-scale solution generates structured shape-patterns that perceptually compete with state-of-the-art methods, whether learning-based or not. Moreover, our interactive solution, which requires no pre-calculation, fits well with the needs of an interactive authoring tool, where the user can not only sketch and extend 2D vector textures but also combine them seamlessly.

Abstract Real‐time character animation in dynamic environments requires the generation of plausible upper‐body movements regardless of the nature of the environment, including non‐rigid obstacles such as vegetation. We propose a flexible model for upper‐body interactions, based on the anticipation of the character's surroundings, and on antagonistic controllers to adapt the amount of muscular stiffness and response time to better deal with obstacles. Our solution relies on a hybrid method for character animation that couples a keyframe sequence with kinematic constraints and lightweight physics. The dynamic response of the character's upper‐limbs leverages antagonistic controllers, allowing us to tune tension/relaxation in the upper‐body without diverging from the reference keyframe motion. A new sight model, controlled by procedural rules, enables high‐level authoring of the way the character generates interactions by adapting its stiffness and reaction time. As results show, our real‐time method offers precise and explicit control over the character's behavior and style, while seamlessly adapting to new situations. Our model is therefore well suited for gaming applications.

Abstract Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on their observation of the environment, and receive appropriate rewards which define the objective. This experience is then used to progressively improve the policy controlling the agent's behavior, typically represented by a neural network. This trained module can then be reused for similar problems, which makes this approach promising for the animation of autonomous, yet reactive characters in simulators, video games or virtual reality environments. This paper surveys the modern Deep Reinforcement Learning methods and discusses their possible applications in Character Animation, from skeletal control of a single, physically‐based character to navigation controllers for individual agents and virtual crowds. It also describes the practical side of training DRL systems, comparing the different frameworks available to build such agents.

Abstract We introduce Delaunay Painting, a novel and easy‐to‐use method to flat‐colour contour‐sketches with gaps. Starting from a Delaunay triangulation of the input contours, triangles are iteratively filled with the appropriate colours, thanks to the dynamic update of flow values calculated from colour hints. Aesthetic finish is then achieved, through energy minimisation of contour‐curves and further heuristics enforcing the appropriate sharp corners. To be more efficient, the user can also make use of our colour diffusion framework, which automatically extends colouring to small, internal regions such as those delimited by hatches. The resulting method robustly handles input contours with strong gaps. As an interactive tool, it minimizes user's efforts and enables any colouring strategy, as the result does not depend on the order of interactions. We also provide an automatized version of the colouring strategy for quick segmentation of contours images, that we illustrate with applications to medical imaging and sketch segmentation.

We present See360, which is a versatile and efficient framework for 360° panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments and render new views of small objects. In contrast, we suggest to tackle camera-centered view synthesis as a 2D affine transformation without using point clouds or depth maps, which enables an effective 360° panoramic scene exploration. Given a pair of reference images, the See360 model learns to render novel views by a proposed novel Multi-Scale Affine Transformer (MSAT), enabling the coarse-to-fine feature rendering. We also propose a Conditional Latent space AutoEncoder (C-LAE) to achieve view interpolation at any arbitrary angle. To show the versatility of our method, we introduce four training datasets, namely UrbanCity360, Archinterior360, HungHom360 and Lab360, which are collected from indoor and outdoor environments for both real and synthetic rendering. Experimental results show that the proposed method is generic enough to achieve real-time rendering of arbitrary views for all four datasets. In addition, our See360 model can be applied to view synthesis in the wild: with only a short extra training time (approximately 10 mins), and is able to render unknown real-world scenes. The superior performance of See360 opens up a promising direction for camera-centered view rendering and 360° panoramic view interpolation.

Crowd motion data is fundamental for understanding and simulating realistic crowd behaviours. Such data is usually collected through controlled experiments to ensure that both desired individual interactions and collective behaviours can be observed. It is however scarce, due to ethical concerns and logistical difficulties involved in its gathering, and only covers a few typical crowd scenarios. In this work, we propose and evaluate a novel Virtual Reality based approach lifting the limitations of real-world experiments for the acquisition of crowd motion data. Our approach immerses a single user in virtual scenarios where he/she successively acts each crowd member. By recording the past trajectories and body movements of the user, and displaying them on virtual characters, the user progressively builds the overall crowd behaviour by him/herself. We validate the feasibility of our approach by replicating three real experiments, and compare both the resulting emergent phenomena and the individual interactions to existing real datasets. Our results suggest that realistic collective behaviours can naturally emerge from virtual crowd data generated using our approach, even though the variety in behaviours is lower than in real situations. These results provide valuable insights to the building of virtual crowd experiences, and reveal key directions for further improvements.

We present a novel, interactive interface for the integrated cleanup, neatening, structuring and vectorization of sketch imagery. Converting scanned raster drawings into vector illustrations is a well-researched set of problems. Our approach is based on a Delaunay subdivision of the raster drawing. We algorithmically generate a colored grouping of Delaunay regions that users interactively refine by dragging and dropping colors. Sketch strokes defined as marking boundaries of different colored regions are automatically neatened using Bézier curves, and turned into closed regions suitable for fills, textures, layering and animation. We show that minimal user interaction using our technique enables better sketch vectorization than state of art automated approaches. A user study, further shows our interface to be simple, fun and easy to use, yet effectively able to process messy images with a mix of construction lines, noisy and incomplete curves, sketched with arbitrary stroke style.

Modern works on style transfer focus on transferring style from a single image. Recently, some approaches study multiple style transfer; these, however, are either too slow or fail to mix multiple styles. We propose ST-VAE, a Variational AutoEncoder for latent space-based style transfer. It performs multiple style transfer by projecting nonlinear styles to a linear latent space, enabling to merge styles via linear interpolation before transferring the new style to the content image. To evaluate ST-VAE, we experiment on COCO for single and multiple style transfer. We also present a case study revealing that ST-VAE outperforms other methods while being faster, flexible, and setting a new path for multiple style transfer.

Efficient urban layout generation is an interesting and important problem in many applications dealing with computer graphics and entertainment. We introduce a novel framework for intuitive and controllable small and large-scale urban layout editing. The key inspiration comes from the observation that cities develop in small incremental changes e.g., a building is replaced, or a new road is created. We introduce a set of atomic operations that consistently modify the city. For example, two buildings are merged, a block is split in two, etc. Our second inspiration comes from volumetric editings, such as clay manipulation, where the manipulated material is preserved. The atomic operations are used in interactive brushes that consistently modify the urban layout. The city is populated with agents. Like volume transfer, the brushes attract or repulse the agents, and blocks can be merged and populated with smaller buildings. We also introduce a large-scale brush that repairs a part of the city by learning style as distributions of orientations and intersections.

Abstract Fashion design often starts with hand‐drawn, expressive sketches that communicate the essence of a garment over idealized human bodies. We propose an approach to automatically dress virtual characters from such input, previously complemented with user‐annotations. In contrast to prior work requiring users to draw garments with accurate proportions over each virtual character to be dressed, our method follows a style transfer strategy : the information extracted from a single, annotated fashion sketch can be used to inform the synthesis of one to many new garment(s) with similar style, yet different proportions. In particular, we define the style of a loose garment from its silhouette and folds, which we extract from the drawing. Key to our method is our strategy to extract both shape and repetitive patterns of folds from the 2D input. As our results show, each input sketch can be used to dress a variety of characters of different morphologies, from virtual humans to cartoon‐style characters.

Abstract Secondary animation effects are essential for liveliness. We propose a simple, real‐time solution for adding them on top of standard skinning, enabling artist‐driven stylization of skeletal motion. Our method takes a standard skeleton animation as input, along with a skin mesh and rig weights. It then derives per‐vertex deformations from the different linear and angular velocities along the skeletal hierarchy. We highlight two specific applications of this general framework, namely the cartoon‐like “squashy” and “floppy” effects, achieved from specific combinations of velocity terms. As our results show, combining these effects enables to mimic, enhance and stylize physical‐looking behaviours within a standard animation pipeline, for arbitrary skinned characters. Interactive on CPU, our method allows for GPU implementation, yielding real‐time performances even on large meshes. Animator control is supported through a simple interface toolkit, enabling to refine the desired type and magnitude of deformation at relevant vertices by simply painting weights. The resulting rigged character automatically responds to new skeletal animation, without further input.

We present a novel method for authoring landscapes with flora and fauna while considering their mutual interactions. Our algorithm outputs a steady-state ecosystem in the form of density maps for each species, their daily circuits, and a modified terrain with eroded trails from a terrain, climatic conditions, and species with related biological information. We introduce the Resource Access Graph, a new data structure that encodes both interactions between food chain levels and animals traveling between resources over the terrain. A novel competition algorithm operating on this data progressively computes a steady-state solution up the food chain, from plants to carnivores. The user can explore the resulting landscape, where plants and animals are instantiated on the fly, and interactively edit it by over-painting the maps. Our results show that our system enables the authoring of consistent landscapes where the impact of wildlife is visible through animated animals, clearings in the vegetation, and eroded trails. We provide quantitative validation with existing ecosystems and a user-study with expert paleontologist end-users, showing that our system enables them to author and compare different ecosystems illustrating climate changes over the same terrain while enabling relevant visual immersion into consistent landscapes.

Abstract Although an important component of natural scenes, the representation of skyscapes is often relatively simplistic. This can be largely attributed to the complexity of the thermodynamics underpinning cloud evolution and wind dynamics, which make interactive simulation challenging. We address this problem by introducing a novel layered model that encompasses both terrain and atmosphere, and supports efficient meteorological simulations. The vertical and horizontal layer resolutions can be tuned independently, while maintaining crucial inter‐layer thermodynamics, such as convective circulation and land‐air transfers of heat and moisture. In addition, we introduce a cloud‐form taxonomy for clustering, classifying and upsampling simulation cells to enable visually plausible, finely‐sampled volumetric rendering. As our results demonstrate, this pipeline allows interactive simulation followed by up‐sampled rendering of extensive skyscapes with dynamic clouds driven by consistent wind patterns. We validate our method by reproducing characteristic phenomena such as diurnal shore breezes, convective cells that contribute to cumulus cloud formation, and orographic effects from moist air driven upslope.

We present a method for easily drafting expressive character animation by playing with instrumented rigid objects. We parse the input 6D trajectories (position and orientation over time) – called spatial motion doodles – into sequences of actions and convert them into detailed character animations using a dataset of parameterized motion clips which are automatically fitted to the doodles in terms of global trajectory and timing. Moreover, we capture the expressiveness of user-manipulation by analyzing Laban effort qualities in the input spatial motion doodles and transferring them to the synthetic motions we generate. We validate the ease of use of our system and the expressiveness of the resulting animations through a series of user studies, showing the interest of our approach for interactive digital storytelling applications dedicated to children and non-expert users, as well as for providing fast drafting tools for animators.

We introduce Dendry, a procedural function that generates dendritic patterns and is locally computable. The function is controlled by parameters such as the level of branching, the degree of local smoothing, random seeding and local disturbance parameters, and the range of the branching angles. It is also controlled by a global control function that defines the overall shape and can be used, for example, to initialize local minima. The algorithm returns the distance to a tree structure which is implicitly constructed on the fly, while requiring a small memory footprint. The evaluation can be performed in parallel for multiple points and scales linearly with the number of cores. We demonstrate an application of our model to the generation of terrain heighfields with consistent river networks. A quad core implementation of our algorithm takes about ten seconds for a 512 × 512 resolution grid on the CPU.

Abstract While analysing and synthesising 2D distributions of points has been applied both to the generation of textures with discrete elements and for populating virtual worlds with 3D objects, the results are often inaccurate since the spatial extent of objects cannot be expressed. We introduce three improvements enabling the synthesis of more general distributions of elements. First, we extend continuous pair correlation function (PCF) algorithms to multi‐class distributions using a dependency graph, thereby capturing interrelationships between distinct categories of objects. Second, we introduce a new normalised metric for disks, which makes the method applicable to both point and possibly overlapping disk distributions. The metric is specifically designed to distinguish perceptually salient features, such as disjoint, tangent, overlapping, or nested disks. Finally, we pay particular attention to convergence of the mean PCF as well as the validity of individual PCFs, by taking into consideration the variance of the input. Our results demonstrate that this framework can capture and reproduce real‐life distributions of elements representing a variety of complex semi‐structured patterns, from the interaction between trees and the understorey in a forest to droplets of water. More generally, it applies to any category of 2D object whose shape is better represented by bounding circles than points.

Abstract Terrains are a crucial component of three‐dimensional scenes and are present in many Computer Graphics applications. Terrain modeling methods focus on capturing landforms in all their intricate detail, including eroded valleys arising from the interplay of varied phenomena, dendritic mountain ranges, and complex river networks. Set against this visual complexity is the need for user control over terrain features, without which designers are unable to adequately express their artistic intent. This article provides an overview of current terrain modeling and authoring techniques, organized according to three categories: procedural modeling, physically‐based simulation of erosion and land formation processes, and example‐based methods driven by scanned terrain data. We compare and contrast these techniques according to several criteria, specifically: the variety of achievable landforms; realism from both a perceptual and geomorphological perspective; issues of scale in terms of terrain extent and sampling precision; the different interaction metaphors and attendant forms of user‐control, and computation and memory performance. We conclude with an in‐depth discussion of possible research directions and outstanding technical and scientific challenges.

Abstract Animating herds of animals while achieving both convincing global shapes and plausible distributions within the herd is difficult, using simulation methods. In this work, we allow users to rely on photos of real herds, which are widely available, for keyframing their animation. More precisely, we learn global and local distribution features in each photo of the input set (which may depict different numbers of animals) and transfer them to the group of animals to be animated, thanks to a new statistical learning method enabling to analyze distributions of ellipses, as well as their density and orientation fields. The animated herd reconstructs the desired distribution at each keyframe while avoiding obstacles. As our results show, our method offers both high‐level user control and help toward realism, enabling to easily author herd animations.

We propose a robust method for untangling an arbitrary number of cloth layers, possibly exhibiting deep interpenetrations, to a collision-free state, ready for animation. Our method relies on an intermediate, implicit representation to solve the problem: the user selects a few garments stored in a library together with their implicit approximations, and places them over a mannequin while specifying the desired order between layers. The intersecting implicit surfaces are then combined using a new family of N-ary composition operators, specially designed for untangling layers. Garment meshes are finally projected to the deformed implicit surfaces in linear time, while best preserving triangles and avoiding loss of details. Each of the untangling operators computes the target surface for a given garment in a single step, while accounting for the order between cloth layers and their individual thicknesses. As a group, they guarantee an intersection-free output configuration. Moreover, a weight can be associated with each layer to tune their relative influence during untangling, such as leather being less deformed than cloth. Results for each layer then reflect the combined effect of the other layers, enabling us to output a plausible configuration in contact regions. As our results show, our method can be used to generate plausible, new static shapes of garments when underwear has been added, as well as collision-free configurations enabling a user to safely launch animations of arbitrarily complex layered clothing.

Chain reaction contraptions, commonly referred to as Rube Goldberg machines, achieve simple tasks in an intentionally complex fashion via a cascading sequence of events. They are fun, engaging and satisfying to watch. Physically realizing them, however, involves hours or even days of manual trial-and-error effort. The main difficulties lie in predicting failure factors over long chains of events and robustly enforcing an expected causality between parallel chains, especially under perturbations of the layout. We present a computational framework to help design the layout of such contraptions by optimizing their robustness to possible assembly errors. Inspired by the active learning paradigm in machine learning, we propose a generic sampling-based method to progressively approximate the success probability distribution of a given scenario over the design space of possible scene layouts. The success or failure of any given simulation is determined from a user-specified causal graph enforcing a time ordering between expected events. Our method scales to complex causal graphs and high dimensional design spaces by dividing the graph and scene into simpler sub-scenarios. The aggregated success probability distribution is subsequently used to optimize the entire layout. We demonstrate the use of our framework through a range of real world examples of increasing complexity, and report significant improvements over alternative approaches. Code and fabrication diagrams are available on the project page.

Abstract We introduce a novel method for interactive generation of visually consistent, snow‐covered landscapes and provide control of their dynamic evolution over time. Our main contribution is the real‐time phenomenological simulation of avalanches and other user‐guided events, such as tracks left by Nordic skiing, which can be applied to interactively sculpt the landscape. The terrain is modeled as a height field with additional layers for stable, compacted, unstable, and powdery snow, which behave in combination as a semi‐viscous fluid. We incorporate the impact of several phenomena, including sunlight, temperature, prevailing wind direction, and skiing activities. The snow evolution includes snow‐melt and snow‐drift, which affect stability of the snow mass and the probability of avalanches. A user can shape landscapes and their evolution either with a variety of interactive brushes, or by prescribing events along a winter season time‐line. Our optimized GPU‐implementation allows interactive updates of snow type and depth across a large (10 × 10km) terrain, including real‐time avalanches, making this suitable for visual assets in computer games. We evaluate our method through perceptual comparison against exiting methods and real snow‐depth data.

Most mountain ranges are formed by the compression and folding of colliding tectonic plates. Subduction of one plate causes large-scale asymmetry while their layered composition (or stratigraphy) explains the multi-scale folded strata observed on real terrains. We introduce a novel interactive modeling technique to generate visually plausible, large scale terrains that capture these phenomena. Our method draws on both geological knowledge for consistency and on sculpting systems for user interaction. The user is provided hands-on control on the shape and motion of tectonic plates, represented using a new geologically-inspired model for the Earth crust. The model captures their volume preserving and complex folding behaviors under collision, causing mountains to grow. It generates a volumetric uplift map representing the growth rate of subsurface layers. Erosion and uplift movement are jointly simulated to generate the terrain. The stratigraphy allows us to render folded strata on eroded cliffs. We validated the usability of our sculpting interface through a user study, and compare the visual consistency of the earth crust model with geological simulation results and real terrains.

Pretend play is a storytelling technique, naturally used from very young ages, which relies on object substitution to represent the characters of the imagined story. We propose a system which assists the storyteller by generating a virtualized story from a recorded dialogue performed with 3D printed figurines. We capture the gestures and facial expressions of the storyteller using Kinect cameras and IMU sensors and transfer them to their virtual counterparts in the story-world. As a proof-of-concept, we demonstrate our system with an improvised story involving a prince and a witch, which was successfully recorded and transferred into 3D animation.

One challenge in portraying large-scale natural scenes in virtual environments is specifying the attributes of plants, such as species, size and placement, in a way that respects the features of natural ecosystems, while remaining computationally tractable and allowing user design. To address this, we combine ecosystem simulation with a distribution analysis of the resulting plant attributes to create biome-specific databases, indexed by terrain conditions, such as temperature, rainfall, sunlight and slope. For a specific terrain, interpolated entries are drawn from this database and used to interactively synthesize a full ecosystem, while retaining the fidelity of the original simulations. A painting interface supplies users with semantic brushes for locally adjusting ecosystem age, plant density and variability, as well as optionally picking from a palette of precomputed distributions. Since these brushes are keyed to the underlying terrain properties a balance between user control and real-world consistency is maintained. Our system can be be used to interactively design ecosystems up to 5 × 5 km2 in extent, or to automatically generate even larger ecosystems in a fraction of the time of a full simulation, while demonstrating known properties from plant ecology such as succession, self-thinning, and underbrush, across a variety of biomes.

Abstract We propose a bi‐layer representation for textures which is suitable for on‐the‐fly synthesis of unbounded textures from an input exemplar. The goal is to improve the variety of outputs while preserving plausible small‐scale details. The insight is that many natural textures can be decomposed into a series of fine scale Gaussian patterns which have to be faithfully reproduced, and some non‐homogeneous, larger scale structure which can be deformed to add variety. Our key contribution is a novel, bi‐layer representation for such textures. It includes a model for spatially‐varying Gaussian noise, together with a mechanism enabling synchronization with a structure layer. We propose an automatic method to instantiate our bi‐layer model from an input exemplar. At the synthesis stage, the two layers are generated independently, synchronized and added, preserving the consistency of details even when the structure layer has been deformed to increase variety. We show on a variety of complex, real textures, that our method reduces repetition artifacts while preserving a coherent appearance.

Abstract One of the major challenges in physically based modelling is making simulations efficient. Adaptive models provide an essential solution to these efficiency goals. These models are able to self‐adapt in space and time, attempting to provide the best possible compromise between accuracy and speed. This survey reviews the adaptive solutions proposed so far in computer graphics. Models are classified according to the strategy they use for adaptation, from time‐stepping and freezing techniques to geometric adaptivity in the form of structured grids, meshes and particles. Applications range from fluids, through deformable bodies, to articulated solids.

Abstract Deformation grammars are a novel procedural framework enabling to sculpt hierarchical 3D models in an object‐dependent manner. They process object deformations as symbols thanks to user‐defined interpretation rules. We use them to define hierarchical deformation behaviours tailored for each model, and enabling any sculpting gesture to be interpreted as some adapted constraint‐preserving deformation. A variety of object‐specific constraints can be enforced using this framework, such as maintaining distributions of subparts, avoiding self‐penetrations or meeting semantic‐based user‐defined rules. The operations used to maintain constraints are kept transparent to the user, enabling them to focus on their design. We demonstrate the feasibility and the versatility of this approach on a variety of examples, implemented within an interactive sculpting system.

We introduce a novel framework for interactive landscape authoring that supports bi-directional feedback between erosion and vegetation simulation. Vegetation and terrain erosion have strong mutual impact and their interplay influences the overall realism of virtual scenes. Despite their importance, these complex interactions have been neglected in computer graphics. Our framework overcomes this by simulating the effect of a variety of geomorphological agents and the mutual interaction between different material and vegetation layers, including rock, sand, humus, grass, shrubs, and trees. Users are able to exploit these interactions with an authoring interface that consistently shapes the terrain and populates it with details. Our method, validated through side-by-side comparison with real terrains, can be used not only to generate realistic static landscapes, but also to follow the temporal evolution of a landscape over a few centuries.

We introduce a deep learning approach for grouping discrete patterns common in graphical designs. Our approach is based on a convolutional neural network architecture that learns a grouping measure defined over a pair of pattern elements. Motivated by perceptual grouping principles, the key feature of our network is the encoding of element shape, context, symmetries, and structural arrangements. These element properties are all jointly considered and appropriately weighted in our grouping measure. To better align our measure with human perceptions for grouping, we train our network on a large, human-annotated dataset of pattern groupings consisting of patterns at varying granularity levels, with rich element relations and varieties, and tempered with noise and other data imperfections. Experimental results demonstrate that our deep-learned measure leads to robust grouping results.

We propose an interactive sculpting system for seamlessly editing pre-computed animations of liquid, without the need for any resimulation. The input is a sequence of meshes without correspondences representing the liquid surface over time. Our method enables the efficient selection of consistent space-time parts of this animation, such as moving waves or droplets, which we call space-time features. Once selected, a feature can be copied, edited, or duplicated and then pasted back anywhere in space and time in the same or in another liquid animation sequence. Our method circumvents tedious user interactions by automatically computing the spatial and temporal ranges of the selected feature. We also provide space-time shape editing tools for non-uniform scaling, rotation, trajectory changes, and temporal editing to locally speed up or slow down motion. Using our tools, the user can edit and progressively refine any input simulation result, possibly using a library of pre-computed space-time features extracted from other animations. In contrast to the trial-and-error loop usually required to edit animation results through the tuning of indirect simulation parameters, our method gives the user full control over the edited space-time behaviors.

Abstract At large scale, landscapes result from the combination of two major processes: tectonics which generate the main relief through crust uplift, and weather which accounts for erosion. This paper presents the first method in computer graphics that combines uplift and hydraulic erosion to generate visually plausible terrains. Given a user‐painted uplift map, we generate a stream graph over the entire domain embedding elevation information and stream flow. Our approach relies on the stream power equation introduced in geology for hydraulic erosion. By combining crust uplift and stream power erosion we generate large realistic terrains at a low computational cost. Finally, we convert this graph into a digital elevation model by blending landform feature kernels whose parameters are derived from the information in the graph. Our method gives high‐level control over the large scale dendritic structures of the resulting river networks, watersheds, and mountains ridges.

Abstract Our work on programmable animation texturing enhances the concept of texture mapping by letting artists stylize arbitrary animations using elementary animations, instantiated at the scale of their choice. The core of our workflow resides in two components: we first impose structure and temporal coherence over the animation data using a novel radius‐based animation‐aware clustering. The computed clusters conform to the user‐specified scale, and follow the underlying animation regardless of its topology. Extreme mesh deformations, complex particle simulations, or simulated mesh animations with ever‐changing topology can therefore be handled in a temporally coherent way. Then, in analogy to fragment shaders that specify an output color based on a texture and a collection of properties defined per vertex (position, texture coordinate, etc.), we provide a programmable interface to the user, letting him or her specify an output animation based on the collection of properties we extract per cluster (position, velocity, etc.). We equip elementary animations with a collection of parameters that are exposed in our programmable system and enables users to script the animated textures depending on properties of the input cluster. We demonstrate the power of our system with complex animated textures created with minimal user input.

Artists, animation and game designers are in demand for solutions to easily populate large virtual environments with crowds that satisfy desired visual features. This paper presents a method to intuitively populate virtual environments by specifying two key features: localized density, being the amount of agents per unit of surface, and localized flow, being the direction in which agents move through a unit of surface. The technique we propose is also time-independant, meaning that whatever the time in the animation, the resulting crowd satisfies both features. To achieve this, our approach relies on the Crowd Patches model. After discretizing the environment into regular patches and creating a graph that links these patches, an iterative optimization process computes the local changes to apply on each patch (increasing/reducing the number of agents in each patch, updating the directions of agents in the patch) in order to satisfy overall density and flow constraints. A specific stage is then introduced after each iteration to avoid the creation of local loops by using a global pathfinding process. As a result, the method has the capacity of generating large realistic crowds in minutes that endlessly satisfy both user specified densities and flow directions, and is robust to contradictory inputs. At last, to ease the design the method is implemented in an artist-driven tool through a painting interface.

We present a phenomenological model for the real-time simulation of paper tearing and sound. The model uses as input rotations of the hand along with the index and thumb of left and right hands to drive the position and orientation of two regions of a sheet of paper. The motion of the hands produces a cone shaped deformation of the paper and guides the formation and growth of the tear. We create a model for the direction of the tear based on empirical observation, and add detail to the tear with a directed noise model. Furthermore, we present a procedural sound synthesis method to produce tearing sounds during interaction. We show a variety of paper tearing examples and discuss applications and limitations.

In this paper we propose a method for the interactive detailed cutting of deformable thin sheets. Our method builds on the ability of frame-based simulation to solve for dynamics using very few control frames while embedding highly detailed geometry - here an adaptive mesh that accurately represents the cut boundaries. Our solution relies on a non-manifold grid to compute shape functions that faithfully adapt to the topological changes occurring while cutting. New frames are dynamically inserted to describe new regions. We provide incremental mechanisms for updating simulation data, enabling us to achieve interactive rates. We illustrate our method with examples inspired by the traditional Kirigami artform.

Abstract Combining procedural generation and user control is a fundamental challenge for the interactive design of natural scenery. This is particularly true for modelling complex waterfall scenes where, in addition to taking charge of geometric details, an ideal tool should also provide a user with the freedom to shape the running streams and falls, while automatically maintaining physical plausibility in terms of flow network, embedding into the terrain, and visual aspects of the waterfalls. We present the first solution for the interactive procedural design of coherent waterfall scenes. Our system combines vectorial editing, where the user assembles elements to create a waterfall network over an existing terrain, with a procedural model that parametrizes these elements from hydraulic exchanges; enforces consistency between the terrain and the flow; and generates detailed geometry, animated textures and shaders for the waterfalls and their surroundings. The tool is interactive, yielding visual feedback after each edit.

Abstract A popular mode of shape synthesis involves mixing and matching parts from different objects to form a coherent whole. The key challenge is to efficiently synthesize shape variations that are plausible, both locally and globally. A major obstacle is to assemble the objects with local consistency, i.e., all the connections between parts are valid with no dangling open connections. The combinatorial complexity of this problem limits existing methods in geometric and/or topological variations of the synthesized models. In this work, we introducereplaceable substructuresas arrangements of parts that can be interchanged while ensuring boundary consistency. The consistency information is extracted from part labels and connections in the original source models. We present a polynomial time algorithm that discovers such substructures by working on a dual of the original shape graph that encodes inter‐part connectivity. We demonstrate the algorithm on a range of test examples producing plausible shape variations, both from a geometric and from a topological viewpoint.

We present a novel approach for the interactive synthesis and editing of virtual worlds. Our method is inspired by painting operations and uses methods for statistical example-based synthesis to automate content synthesis and deformation. Our real-time approach takes a form of local inverse procedural modeling based on intermediate statistical models: selected regions of procedurally and manually constructed example scenes are analyzed, and their parameters are stored as distributions in a palette, similar to colors on a painter's palette. These distributions can then be interactively applied with brushes and combined in various ways, like in painting systems. Selected regions can also be moved or stretched while maintaining the consistency of their content. Our method captures both distributions of elements and structured objects, and models their interactions. Results range from the interactive editing of 2D artwork maps to the design of 3D virtual worlds, where constraints set by the terrain's slope are also taken into account.

We present a space-time abstraction for the sketch-based design of character animation. It allows animators to draft a full coordinated motion using a single stroke called the space-time curve (STC). From the STC we compute a dynamic line of action (DLOA) that drives the motion of a 3D character through projective constraints. Our dynamic models for the line's motion are entirely geometric, require no pre-existing data, and allow full artistic control. The resulting DLOA can be refined by over-sketching strokes along the space-time curve, or by composing another DLOA on top leading to control over complex motions with few strokes. Additionally, the resulting dynamic line of action can be applied to arbitrary body parts or characters. To match a 3D character to the 2D line over time, we introduce a robust matching algorithm based on closed-form solutions, yielding a tight match while allowing squash and stretch of the character's skeleton. Our experiments show that space-time sketching has the potential of bringing animation design within the reach of beginners while saving time for skilled artists.

We present the first sketch-based modeling method for developable surfaces with pre-designed folds, such as garments or leather products. The main challenge we address for building folded surfaces from sketches is that silhouette strokes on the sketch correspond to discontinuous sets of non-planar curves on the 3D model. We introduce a new zippering algorithm for progressively identifying silhouette edges on the model and tying them to silhouette strokes. Our solution ensures that the strokes are fully covered and optimally sampled by the model. This new method, interleaved with developability optimization steps, is implemented in a multiview sketching system where the user can sketch the contours of internal folds in addition to the usual silhouettes, borders, and seam lines. All strokes are interpreted as hard constraints, while developability is only optimized. The developability error map we provide then enables users to add local seams or darts where needed and progressively improve their design. This makes our method robust, even to coarse input for which no fully developable solution exists.

We present the first method to animate sheets of paper at interactive rates, while automatically generating a plausible set of sharp features when the sheet is crumpled. The key idea is to interleave standard physically based simulation steps with procedural generation of a piecewise continuous developable surface. The resulting hybrid surface model captures new singular points dynamically appearing during the crumpling process, mimicking the effect of paper fiber fracture. Although the model evolves over time to take these irreversible damages into account, the mesh used for simulation is kept coarse throughout the animation, leading to efficient computations. Meanwhile, the geometric layer ensures that the surface stays almost isometric to its original 2D pattern. We validate our model through measurements and visual comparison with real paper manipulation, and show results on a variety of crumpled paper configurations.

In this talk, I will review the recent advances in Computer Graphics towards more expressive modeling techniques. Based on a new methodology that combines knowledge-based models with expressive user controls, these methods are making 3D modeling and animation faster and easier for artists, and should soon put them at the reach of the general public. I will also identify a number of new challenges this research brings for geometric computing.

Abstract We introduce “Crowd Sculpting”: a method to interactively design populated environments by using intuitive deformation gestures to drive both the spatial coverage and the temporal sequencing of a crowd motion. Our approach assembles large environments from sets of spatial elements which contain inter‐connectible, periodic crowd animations. Such a “Crowd Patches” approach allows us to avoid expensive and difficult‐to‐control simulations. It also overcomes the limitations of motion editing, that would result into animations delimited in space and time. Our novel methods allows the user to control the crowd patches layout in ways inspired by elastic shape sculpting: the user creates and tunes the desired populated environment through stretching, bending, cutting and merging gestures, applied either in space or time. Our examples demonstrate that our method allows the space‐time editing of very large populations and results into endless animation, while offering real‐time, intuitive control and maintaining animation quality.

We present a novel approach to interactive character skinning, which is robust to extreme character movements, handles skin contacts and produces the effect of skin elasticity (sliding). Our approach builds on the idea of implicit skinning in which the character is approximated by a 3D scalar field and mesh-vertices are appropriately re-projected. Instead of being bound by an initial skinning solution used to initialize the shape at each time step, we use the skin mesh to directly track iso-surfaces of the field over time. Technical problems are two-fold: firstly, all contact surfaces generated between skin parts should be captured as iso-surfaces of the implicit field; secondly, the tracking method should capture elastic skin effects when the joints bend, and as the character returns to its rest shape, so the skin must follow. Our solutions include: new composition operators enabling blending effects and local self-contact between implicit surfaces, as well as a tangential relaxation scheme derived from the as-rigid-as possible energy to solve the tracking problem.

The automated computation of appropriate viewpoints in complex 3D scenes is a key problem in a number of computer graphics applications. In particular, crowd simulations create visually complex environments with many simultaneous events for which the computation of relevant viewpoints remains an open issue. In this paper, we propose a system which enables the conveyance of events occurring in complex crowd simulations. The system relies on Reynolds' model of steering behaviors to control and locally coordinate a collection of camera agents similar to a group of reporters. In our approach, camera agents are either in a scouting mode, searching for relevant events to convey, or in a tracking mode following one or more unfolding events. The key benefit, in addition to the simplicity of the steering rules, holds in the capacity of the system to adapt to the evolving complexity of crowd simulations by self-organizing the camera agents to track interesting events.

Abstract In this paper, we propose a new paradigm for free‐form shape deformation. Standard deformable models minimize an energy measuring the distance to a single target shape. We propose a new, “mutable” elastic model. It represents complex geometry by a collection of parts and measures the distance of each part measures to a larger set of alternative rest configurations. By detecting and reacting to local switches between best‐matching rest states, we build a 3D sculpting system: It takes a structured shape consisting of parts and replacement rules as input. The shape can subsequently be elongated, compressed, bent, cut, and merged within a constraints‐based free‐form editing interface, where alternative rest‐states model to such changes. In practical experiments, we show that the approach yields a surprisingly intuitive and easy to implement interface for interactively designing objects described by such discrete shape grammars, for which direct shape control mechanisms were typically lacking.

Abstract Extraction of skeletons from solid shapes has attracted quite a lot of attention, but less attention was paid so far to the reverse operation: generating smooth surfaces from skeletons and local radius information. Convolution surfaces, i.e. implicit surfaces generated by integrating a smoothing kernel along a skeleton, were developed to do so. However, they failed to reconstruct prescribed radii and were unable to model large shapes with fine details. This work introduces SCALe‐invariant Integral Surfaces (SCALIS), a new paradigm for implicit modelling from skeleton graphs. Similarly to convolution surfaces, our new surfaces still smoothly blend when field contributions from new skeleton parts are added. However, in contrast with convolution surfaces, blending properties are scale‐invariant. This brings three major benefits: the radius of the surface around a skeleton can be explicitly controlled, shapes generated in blending regions are self‐similar regardless of the scale of the model and thin shape components are not excessively smoothed out when blended into larger ones.

Characters with precise internal anatomy are important in film and visual effects, as well as in medical applications. We propose the first semi-automatic method for creating anatomical structures, such as bones, muscles, viscera and fat tissues. This is done by transferring a reference anatomical model from an input template to an arbitrary target character, only defined by its boundary representation (skin). The fat distribution of the target character needs to be specified. We can either infer this information from MRI data, or allow the users to express their creative intent through a new editing tool. The rest of our method runs automatically: it first transfers the bones to the target character, while maintaining their structure as much as possible. The bone layer, along with the target skin eroded using the fat thickness information, are then used to define a volume where we map the internal anatomy of the source model using harmonic (Laplacian) deformation. This way, we are able to quickly generate anatomical models for a large range of target characters, while maintaining anatomical constraints.

We introduce a new family of binary composition operators that solves four major problems of constructive implicit modeling: suppressing bulges when two shapes merge, avoiding unwanted blending at a distance, ensuring that the resulting shape keeps the topology of the union, and enabling sharp details to be added without being blown up. The key idea is that field functions should not only be combined based on their values, but also on their gradients . We implement this idea through a family of C ∞ composition operators evaluated on the GPU for efficiency, and illustrate it by applications to constructive modeling and animation.

The line of action is a conceptual tool often used by cartoonists and illustrators to help make their figures more consistent and more dramatic. We often see the expression of characters---may it be the dynamism of a super hero, or the elegance of a fashion model---well captured and amplified by a single aesthetic line. Usually this line is laid down in early stages of the drawing and used to describe the body's principal shape. By focusing on this simple abstraction, the person drawing can quickly adjust and refine the overall pose of his or her character from a given viewpoint. In this paper, we propose a mathematical definition of the line of action (LOA), which allows us to automatically align a 3D virtual character to a user-specified LOA by solving an optimization problem. We generalize this framework to other types of lines found in the drawing literature, such as secondary lines used to place arms. Finally, we show a wide range of poses and animations that were rapidly created using our system.

Geometric skinning techniques, such as smooth blending or dual-quaternions, are very popular in the industry for their high performances, but fail to mimic realistic deformations. Other methods make use of physical simulation or control volume to better capture the skin behavior, yet they cannot deliver real-time feedback. In this paper, we present the first purely geometric method handling skin contact effects and muscular bulges in real-time. The insight is to exploit the advanced composition mechanism of volumetric, implicit representations for correcting the results of geometric skinning techniques. The mesh is first approximated by a set of implicit surfaces. At each animation step, these surfaces are combined in real-time and used to adjust the position of mesh vertices, starting from their smooth skinning position. This deformation step is done without any loss of detail and seamlessly handles contacts between skin parts. As it acts as a post-process, our method fits well into the standard animation pipeline. Moreover, it requires no intensive computation step such as collision detection, and therefore provides real-time performances.

We present a fully automatic method for design-preserving transfer of garments between characters with different body shapes. For real-life garments, such transfer is performed through a knowledge intensive and time consuming process, known as pattern grading . Our first contribution is to reformulate the criteria used in professional pattern-grading as a set of geometric requirements, respectively expressing shape or design preservation, proportionality, and fit. We then propose a fully automatic garment transfer algorithm which satisfies all of these criteria while ensuring the physical plausibility of the result. Specifically, we formulate garment transfer as a constrained optimization problem and solve it efficiently through iterative quadratic minimization. As demonstrated by our results, our method is able to automatically generate design-preserving versions of existing garments for target characters whose proportions and body shape significantly differ from those of the source. The method correctly handles the transfer of multiple layers of garment. Lastly, when source 2D patterns are available, we output graded patterns suitable for manufacturing the transferred garments. Our fully automatic design-preserving transfer method leads to significant time savings for both computer artists and fashion designers.

Abstract Blending is both the strength and the weakness of functionally based implicit surfaces (such as F‐reps or soft‐objects). While it gives them the unique ability to smoothly merge into a single, arbitrary shape, it makes implicit modelling hard to control since implicit surfaces blend at a distance, in a way that heavily depends on the slope of the field functions that define them. This paper presents a novel, generic solution to blending of functionally‐based implicit surfaces: the insight is that to be intuitive and easy to control, blends should be located where two objects overlap, while enabling other parts of the objects to come as close to each other as desired without being deformed. Our solution relies on automatically defined blending regions around the intersection curves between two objects. Outside of these volumes, a clean union of the objects is computed thanks to a new operator that guarantees the smoothness of the resulting field function; meanwhile, a smooth blend is generated inside the blending regions. Parameters can automatically be tuned in order to prevent small objects from blurring out when blended into larger ones, and to generate a progressive blend when two animated objects come in contact.

Moving garments and other cloth objects exhibit dynamic, complex wrinkles. Generating such wrinkles in a virtual environment currently requires either a time-consuming manual design process, or a computationally expensive simulation, often combined with accurate parameter-tuning requiring specialized animator skills. Our work presents an alternative approach for wrinkle generation which combines coarse cloth animation with a post-processing step for efficient generation of realistic-looking fine dynamic wrinkles. Our method uses the stretch tensor of the coarse animation output as a guide for wrinkle placement. To ensure temporal coherence, the placement mechanism uses a space-time approach allowing not only for smooth wrinkle appearance and disappearance, but also for wrinkle motion, splitting, and merging over time. Our method generates believable wrinkle geometry using specialized curve-based implicit deformers. The method is fully automatic and has a single user control parameter that enables the user to mimic different fabrics.

Abstract We present a general method to intuitively create a wide range of locomotion controllers for 3D legged characters. The key of our approach is the assumption that efficient locomotion can exploit the natural vibration modes of the body, where these modes are related to morphological parameters such as the shape, size, mass, and joint stiffness. The vibration modes are computed for a mechanical model of any 3D character with rigid bones, elastic joints, and additional constraints as desired. A small number of vibration modes can be selected with respect to their relevance to locomotion patterns and combined into a compact controller driven by very few parameters. We show that these controllers can be used in dynamic simulations of simple creatures, and for kinematic animations of more complex creatures of a variety of shapes and sizes.

Abstract Films like Shrek, Madagascar, The Chronicles of Narnia and Charlotte's web all have something in common: realistic quadruped animations. While the animation of animals has been popular for a long time, the technical challenges associated with creating highly realistic, computer generated creatures have been receiving increasing attention recently. The entertainment, education and medical industries have increased the demand for simulation of realistic animals in the computer graphics area. In order to achieve this, several challenges need to be overcome: gathering and processing data that embodies the natural motion of an animal – which is made more difficult by the fact that most animals cannot be easily motion‐captured; building accurate kinematic models for animals, with adapted animation skeletons in particular; and developing either kinematic or physically‐based animation methods, either by embedding some a priori knowledge about the way that quadrupeds locomote and/or adopting examples of real motion. In this paper, we present an overview of the common techniques used to date for realistic quadruped animation. This includes an outline of the various ways that realistic quadruped motion can be achieved, through video‐based acquisition, physics based models, inverse kinematics or some combination of the above.

Abstract Modeling natural elements such as trees in a plausible way, while offering simple and rapid user control, is a challenge. This paper presents a method based on a new structurefrom silhouettesparadigm. We claim that sketching the silhouettes of foliage at multiple scales is quicker and more intuitive for a user than having to sketch each branch of a tree. This choice allows us to incorporate botanical knowledge, enabling us to infer branches that connect in a plausible way to their parent branch and have a correct distribution in 3D. We illustrate these ideas by presenting a seamless sketch‐based interface, used for sketching foliage silhouettes from the scale of an entire tree to the scale of a leaf. Each sketch serves for inferring both the branches at that level and construction lines to serve as support for sub‐silhouette refinement. When the user finally zooms out, the style inferred for the branching systems he has refined (in terms of branch density, angle, length distribution and shape) is duplicated to the unspecified branching systems at the same level. Meanwhile, knowledge from botany is again used for extending the branch distribution to 3D, resulting in a full, plausible 3D tree that fits the user‐sketched contours. As our results show, this system can be of interest to both experts and novice users. While experts can fully specify all parts of a tree and over‐sketch specific branches if required, any user can design a basic 3D tree in one or two minutes, as easily as sketching it with paper and pen.

This paper presents a new interaction system designed for hands-on 3D shape modeling and deformation through natural hand gestures. Our system is made of a Phantom haptic device coupled with a deformable foam ball that supports pressure sensors. These sensors detect forces exerted by the user's fingertips, and are used to control the configuration of a compliant virtual hand that is modeling soft virtual clay. During interaction, the user is provided both passive tactile feedback through the foam ball, and realistic visual feedback since the virtual hand deforms due to its interaction in the virtual environment. The combination of all these feedbacks provides the artist with a good immersion allowing for effective sculpting in a virtual world.

This paper presents a novel interaction system, aimed at hands-on manipulation of digital models through natural hand gestures. Our system is composed of a new physical interaction device coupled with a simulated compliant virtual hand model. The physical interface consists of a SpaceNavigator, augmented with pressure sensors to detect directional forces applied by the user's fingertips. This information controls the position, orientation, and posture of the virtual hand in the same way that the SpaceNavigator uses measured forces to animate a virtual frame. In this manner, user control does not involve fatigue due to reaching gestures or holding a desired hand shape. During contact, the user has a realistic visual feedback in the form of plausible interactions between the virtual hand and its environment. Our device is well suited to any situation where hand gesture, contact, or manipulation tasks need to be performed in virtual. We demonstrate the device in several simple virtual worlds and evaluate it through a series of user studies.

Abstract Generating plausible deformations of a character skin within the standard production pipeline is a challenge. This paper presents a volume preservation method dedicated to skinned characters. As usual, the character is defined by a skin mesh at some rest pose and an animation skeleton. At each animation step, skin deformations are first computed using standard SSD. Our method corrects the result using a set of local deformations which model the fold‐over‐free, constant volume behavior of soft tissues. This is done geometrically, without the need of any physically‐based simulation. To make the method easily applicable, we also provide automatic ways to extract the local regions where volume is to be preserved and to compute adequate skinning weights, both based on the character's morphology.

This paper explores a sketch-based interface for quickly yet accurately creating visually realistic hair for virtual characters. Recently, physically-based models have proved successful for generating a wide variety of hair types, but they do not provide a straightforward method for designing target hairstyles. The contribution of this paper is to propose a user-friendly method for controlling such a physically-based model, requiring no specific knowledge of mechanics or hair styling: the user sketches example hair strands over a side view of the character's head, or alternatively annotates a picture of real hair viewed from the side serving as a reference. We show how the sketch can be used to infer the geometric and mechanical properties of the hair strands, to adjust the shape of the scalp, and to generate an adequate hair volume. Our method is validated on a wide variety of hair styles, from straight to curly and short to long hair.

Realistic hair modeling is a fundamental part of creating virtual humans in computer graphics. This paper surveys the state of the art in the major topics of hair modeling: hairstyling, hair simulation, and hair rendering. Because of the difficult, often unsolved problems that arise in all these areas, a broad diversity of approaches are used, each with strengths that make it appropriate for particular applications. We discuss each of these major topics in turn, presenting the unique challenges facing each area and describing solutions that have been presented over the years to handle these complex issues. Finally, we outline some of the remaining computational challenges in hair modeling.

Abstract Modeling dressed characters is known as a very tedious process. It usually requires specifying 2D fabric patterns, positioning and assembling the min 3D, and then performing a physically‐based simulation. The latter accounts for gravity and collisions to compute the rest shape of the garment, with the adequate folds and wrinkles. This paper presents a more intuitive way to design virtual clothing. We start with a 2D sketching system in which the user draws the contours and seam‐lines of the garment directly on a virtual mannequin. Our system then converts the sketch into an initial 3D surface using an existing method based on a precomputed distance field around the mannequin. The system then splits the created surface into different panels delimited by the seam‐lines. The generated panels are typically not developable. However, the panels of a realistic garment must be developable, since each panel must unfold into a 2D sewing pattern. Therefore our system automatically approximates each panel with a developable surface, while keeping them assembled along the seams. This process allows us to output the corresponding sewing patterns. The last step of our method computes a natural rest shape for the 3D garment, including the folds due to the collisions with the body and gravity. The folds are generated using procedural modeling of the buckling phenomena observed in real fabric. The result of our algorithm consists of a realistic looking 3D mannequin dressed in the designed garment and the 2D patterns which can be used for distortion free texture mapping. The patterns we create also allow us to sew real replicas of the virtual garments. Keywords:Geometric modeling of garments, developable surfaces, procedural models, buckling. Categories and Subject Descriptors (according to ACM CCS): I.3.5 [Computing Methodologies/Computer Graphics]: Surface representations, I.3.7 [Computing Methodologies/Computer Graphics]: Three‐dimensional graphics and realism

Simulating human hair is recognized as one of the most difficult tasks in computer animation. In this paper, we show that the Kirchhoff equations for dynamic, inextensible elastic rods can be used for accurately predicting hair motion. These equations fully account for the nonlinear behavior of hair strands with respect to bending and twisting. We introduce a novel deformable model for solving them: each strand is represented by a Super-Helix , i.e., a piecewise helical rod which is animated using the principles of Lagrangian mechanics. This results in a realistic and stable simulation, allowing large time steps. Our second contribution is an in-depth validation of the Super-Helix model, carried out through a series of experiments based on the comparison of real and simulated hair motions. We show that our model efficiently handles a wide range of hair types with a high level of realism.

Abstract Interactive environments for dynamically deforming objects play an important role in surgery simulation and entertainment technology. These environments require fast deformable models and very efficient collision handling techniques. While collision detection for rigid bodies is well investigated, collision detection for deformable objects introduces additional challenging problems. This paper focuses on these aspects and summarizes recent research in the area of deformable collision detection. Various approaches based on bounding volume hierarchies, distance fields and spatial partitioning are discussed. In addition, image‐space techniques and stochastic methods are considered. Applications in cloth modeling and surgical simulation are presented.

This paper proposes a new method for designing dynamic wrinkles that appear and disappear according to the underlying deformation of tissues. The user positions and orients wrinkling tools on a mesh. During animation, geometric wrinkles are generated in real-time in the regions covered by the tools, mimicking resistance to compression of tissues. The wrinkling feature can be added to any existing animation. When the local resolution of the mesh is not sufficient, our tool refines it according to the wrinkle's finest feature. As our results show, the technique can be applied to a variety of situations such as facial expression wrinkles, joint wrinkles or garment wrinkles.

Swirling-sweepers is a new method for modeling shapes while preserving volume. The artist describes a deformation by dragging a point along a path. The method is independent of the geometric representation of the shape. It preserves volume and avoids self-intersections, both local and global. It is capable of unlimited stretching and the deformation can be constrained to affect only apart of the model. We argue that all of these properties are necessary for interactive modeling if the user is to have the impression that he or she is shaping a real material. Our method is the first to implement all five.

We present Sweepers, a new class of space deformations suitable for interactive virtual sculpture. The artist describes a basic deformation as a path through which a tool is moved. Our tools are simply shapes, subsets of 3D space. So we can use shapes already created as customized tools to make more complex shapes or to simplify the modeling process. When a tool is moved it causes a deformation of the working shape along the path of the tool. This is in accordance with a clay modeling metaphor and easy to understand and predict. More complicated deformations are achieved by using several tools simultaneously in the same region. It is desirable that deformations for modeling are 'foldover-free' that is part of deformed space cannot overlap so that the deformations are reversible. There are good intuitive reasons to believe that our deformations are foldover-free but we have not yet completed a proof. We have an efficient formulation for a single tool following a simple path (translation, scaling or rotation) and we can demonstrate the effects of multiple tools used simultaneously. For representing shapes, we present a mesh refinement and decimation algorithm that takes advantage of the definition of our deformations. The prototype implementation described has been used to create a variety of models quickly and conveniently.

This research work is aimed toward the development of a VR-based trainer for colon cancer removal. It enables the surgeons to interactively view and manipulate the concerned virtual organs as during a real surgery. First, we present a method for animating the small intestine and the mesentery (the tissue that connects it to the main vessels) in real-time, thus enabling user interaction through virtual surgical tools during the simulation. We present a stochastic approach for fast collision detection in highly deformable, self-colliding objects. A simple and efficient response to collisions is also introduced in order to reduce the overall animation complexity. Second, we describe a new method based on generalized cylinders for fast rendering of the intestine. An efficient curvature detection method, along with an adaptive sampling algorithm, is presented. This approach, while providing improved tessellation without the classical self-intersection problem, also allows for high-performance rendering thanks to the new 3D skinning feature available in recent GPUs. The rendering algorithm is also designed to ensure a guaranteed frame rate. Finally, we present the quantitative results of the simulations and describe the qualitative feedback obtained from the surgeons.

This paper presents a method for animating and rendering an interactive natural scenery in real-time. It improves the prairie model of [I I I] by enabling the on-the-fly generation of blades of grass, at three different levels of detail, from user-specified density maps. A new animation function, the tread on grass, is defined to allow virtual objects or characters to crush the grass. The resulting grass model is incorporated into a more complex natural scene with the adjunction of trees that respond to the same wind. Results are illustrated by the real-time animation of autonomous virtual humans interacting with this natural scenery.

Making virtual modeling as easy and intuitive as real-clay manipulation is still an unsolved problem. This paper takes a step in this direction: in addition to offering standard features such as addition and removal of material, it uses a new real-time plasticity model to let the user apply local and global deformations such as those made in real clay by pressing with a finger or bending a sculpture with one hands. Although not completely physically accurate, the model exhibits several important features of real clay, namely plasticity, mass conservation, and surface tension effects. These features make the model intuitive, since the user obtains the shapes he expects, as demonstrated by our results.

Interactive implicit modelling with complex skeletons was improved with the introduction of primitives defined at different LODs. These implicit primitives use a subdivision curve as a skeleton. In this paper an extension to this representation is presented, in order to make it suitable for the interactive modelling and animation of soft objects in contact situations. The first contribution improves the display method for subdivision-based implicit primitives; this uses an adaptive polygonisation which locally refines, where necessary, according to the currently selected LOD. The second contribution consists of a new method for preventing unwanted blending when a skeleton-curve folds back onto itself. The third introduces local deformations where surfaces that should not blend come into contact. We illustrate the benefits of this methodology by describing two applications: the interactive modelling of complex organic shapes in contact situations and the physically-based animation of such organic shapes.

We present a multi-scale algorithm for mapping a texture defined by an input image onto an arbitrary surface. It avoids the generation and storage of a new, specific texture. The idea is to progressively cover the surface by texture patches of various sizes and shapes, selected from a single input image. The process starts with large patches. A mapping that minimizes the texture fitting error with already textured neighbouring patches is selected. When this error is above a threshold, the patch is split into smaller ones, and the algorithm recursively looks for good fits at a smaller scale. The process ends when the surface is entirely covered. Our results show that the method correctly handles a wide set of texture patterns, which can be used at different mapping scales. Hierarchical texture mapping only outputs texture coordinates in the original texture for each triangle of the initial mesh. Rendering is therefore easy and memory cost minimal. Moreover the initial geometry is preserved.

Generation of dynamic natural scenes is essential for real-time applications, such as simulators or video-games. This paper presents a method for animating and rendering a prairie in real time. The geometric model for the grass relies on three different levels of detail: 3D geometry, volumetric textures (called here 2.5D representation), and 2D textures. The animation of these LODs is controlled through procedural animation primitives that implement wind effects such as slight breeze, gust of wind, whirlwind, or blast of air due to a flying object. Smooth transitions between levels of detail are computed “on the fly ” according to camera motion, without stopping the animation. We discuss real-time performance on two platforms: an SGI O2, and an ONYX 2 with an Infinite Reality board.

This paper presents a robust, adaptive method for animating dynamic visco-elastic deformable objects that provides a guaranteed frame rate. Our approach uses a novel automatic space and time adaptive level of detail technique, in combination with a large-displacement (Green) strain tensor formulation. The body is partitioned in a non-nested multiresolution hierarchy of tetrahedral meshes. The local resolution is determined by a quality condition that indicates where and when the resolution is too coarse. As the object moves and deforms, the sampling is refined to concentrate the computational load into the regions that deform the most. Our model consists of a continuous differential equation that is solved using a local explicit finite element method. We demonstrate that our adaptive Green strain tensor formulation suppresses unwanted artifacts in the dynamic behavior, compared to adaptive mass-spring and other adaptive approaches. In particular, damped elastic vibration modes are shown to be nearly unchanged for several levels of refinement. Results are presented in the context of a virtual reality system. The user interacts in real-time with the dynamic object through the control of a rigid tool, attached to a haptic device driven with forces derived from the method.

To remain an attractive model, skeleton-based implicit surfaces have to allow the design and display of shapes at interactive rates. We focus on surfaces whose skeletons are graphs of interconnected curves. We present subdivision-curve primitives that rely on convolution for generating bulge-free and crease-free implicit surfaces. These surfaces are efficiently yet correctly displayed using local meshes around each curve that locally overlap in blending regions. Subdivision-curve primitives offer a practical solution to the unwanted-blending problem that ensures C/sup 1/ continuity everywhere. Moreover, they can be used to generate representations at different levels of detail, enabling the interactive display of at least a coarse version of the objects, whatever the performance of the workstation.

We present a system for sketching in 3D, which strives to preserve the degree of expression, imagination, and simplicity of use achieved by 2D drawing. Our system directly uses user-drawn strokes to infer the sketches representing the same scene from different viewpoints, rather than attempting to reconstruct a 3D model. This is achieved by interpreting strokes as indications of a local surface silhouette or contour. Strokes thus deform and disappear progressively as we move away from the original viewpoint. They may be occluded by objects indicated by other strokes, or, in contrast, be drawn above such objects. The user draws on a plane which can be positioned explicitly or relative to other objects or strokes in the sketch. Our system is interactive, since we use fast algorithms and graphics hardware for rendering. We present applications to education, design, architecture and fashion, where 3D sketches can be used alone or as an annotation of an existing 3D model.

This paper presents an adaptive technique to animate deformable bodies in real-time. Our method relies on mixed finite-volume/finite-element method applied to an arbitrary non-nested hierarchy of volumetric meshes. We achieve a guaranteed frame rate thanks to a innovative multi-resolution algorithm that locally refines of simplifies the simulated object in order to concentrate computation load where and when needed.

We present a simple method for performing real-time collision detection in a virtual surgery environment. The method relies on the graphics hardware for testing the interpenetration between a virtual deformable organ and a rigid tool controlled by the user. The method enables to take into account the motion of the tool between two consecutive time steps. For our specific application, the new method runs about a hundred times faster than the well known oriented-bonding-boxes tree method.

We present a texturing method that correctly maps homogeneous non-periodic textures to arbitrary surfaces without any of the difficulties usually encountered using existing tools.Our technique requires little redundant designer work, has low time and memory costs during rendering and provides high texture resolution.The idea is simple: a few triangular texture samples, which obey specific boundary conditions, are chosen from the desired pattern and mapped in a non-periodic fashion onto the surface.Our mapping algorithm enables us to freely tune the scale of the texture with respect to the object's geometry, while minimizing distortions.Moreover, it yields singularity-free texturing whatever the topology of the object.The sets of texture samples may be created interactively from pictures or drawings.We also provide two alternative methods for automatically generating them, defined as extensions of Perlin's and Worley's procedural texture synthesis techniques.As our results show, the method produces textured objects that look reasonable from any viewpoint and can be used in real-time applications.

This paper surveys the set of techniques developed in computer graphics for animating human walking. First we focus on the evolution from purely kinematic ‘knowledge-based’ methods to approaches that incorporate dynamic constraints or use dynamic simulations to generate motion. Then we review the recent advances in motion editing that enable the control of complex animations by interactively blending and tuning synthetic or captured motions. Copyright © 1999 John Wiley & Sons, Ltd.

We present a new method to reconstruct an implicit representation of a branching object from a set of data points scattered on its surface. The method is based on the computation of a geometric skeleton inside the data set. This skeleton is simplified in order to filter noise and converted into skeletal elements – a graph of interconnected curves – that generate an implicit surface. We use Bézier triangles as extra skeletal elements to perform bulge free blends between branches while controlling the blend extent. The result is a smooth reconstruction of the object, that can be computed whatever its topology. The skeleton offers compact storage, and provides an underlying structure for the reconstructed object, making it easier to edit in a modeling or animation environment.

The paper presents a general approach for designing and animating complex deformable models with implicit surfaces. Implicit surfaces are introduced as an extra layer coating any kind of structure that moves and deforms over time. Offering a compact definition of a smooth surface around an object, they provide an efficient collision detection mechanism. The implicit layer deforms in order to generate exact contact surfaces between colliding bodies. A simple physically based model approximating elastic behavior is then used for computing collision response. The implicit formulation also eases the control of the object's volume with a new method based on local controllers. We present two different applications that illustrate the benefits of these techniques. First, the animation of simple characters made of articulated skeletons coated with implicit flesh exploits the compactness and enhanced control of the model. The second builds on the specific properties of implicit surfaces for modeling soft inelastic substances capable of separation and fusion that maintain a constant volume when animated.

3D models of the lips have been developed in the framework of an audio visual articulatory speech synthesizer. Unlike most of the regions of the human face, the lips are essentially characterized by their border contours. The internal and external contours of the vermilion zone can be fitted by means of algebraic equations. The coefficients of these equations must be controlled so that the lip shape can be adapted to speaker dependent conformations and to any speech "gesture". To reach this goal, a 3D model of the lips has been based on a geometrical analysis of the natural lips of a French speaker. Our lip model was developed by adjusting a set of continuous functions best fitting the contours of 22 reference lip shapes. Only five parameters are necessary to predict all the equations of the contours of the lip model. From this model, a volumetric model based on implicit surfaces was also developed to take into account lip contact.

Abstract This paper presents a novel approach for facilitating the use of physically based models by animators. The idea is to let the user guide motion at a high level of control by giving approximate desired trajectories and synchronization constraints between the objects over time, while a simulation module computes the final motion, dealing with collision detection and response, and enhancing realism. The objects, which are either isolated or components of an articulated structure, are guided through the specification of key‐positions and orientations, defined by coordinates that can be fixed or relative to another object. The animation sequence is scripted by specifying a graph of synchronization constraints between objects over time. During the animation, objects automatically regulate their speed in order to meet these constraints.

This paper presents a hybrid model for animation of soft inelastic substance which undergo topological changes, e.g. separation and fusion and which fit with the objects they are in contact with. The model uses a particle system coated with a smooth iso-surface that is used for performing collision detection, precise contact modeling and integration of response forces. The animation technique solves three problems inherent in implicit modeling. Firstly, local volume controllers are defined to insure constant volume deformation, even during highly inelastic processes such as splitting or fusion. Secondly, we avoid unwanted distance blending between disconnected pieces of the same substance. Finally, we simulate both collisions and progressive merging under compression between implicit surfaces that do not blend together. Parameter tuning is facilitated by the layered model and animation is generated at interactive rates. Keywords: implicit surface, physics-based animation, inelasticity. 1

Abstract This paper presents a new method that combines a medial axis and implicit surfaces in order to reconstruct a 3D solid from an unstructured set of points scattered on the object's surface. The representation produced is based on iso‐surfaces generated by skeletons, and is a particularly compact way of defining a smooth free‐form solid. The method is based on the minimisation of an energy representing a “distance” between the set of data points and the iso‐surface, resembling previous reserach19. Initialisation, however, is more robust and efficient since there is computation of the medial axis of the set of points. Instead of subdividing existing skeletons in order to refine the object's surface, a new reconstruction algorithm progressively selects skeleton‐points from the pre‐ computed medial axis using an heuristic principle based on a “local energy” criterion. This drastically speeds up the reconstruction process. Moreover, using the medial axis allows reconstruction of objects with complex topology and geometry, like objects that have holes and branches or that are composed of several connected components. This process is fully automatic. The method has been successfully applied to both synthetic and real data.

Abstract This paper describes a method that facilitates the use of physically‐based models by animators. The main point is to give the animator a familiar interface, while providing a simulation module which detects collisions, thus enhancing realism. The user gives a set of key‐frames to guide motion, but does not have to address problems such as interpenetration avoidance, deformations due to collisions, or realism of motion. The simulator will correct the trajectories and compute deformations according to each object's physical properties (such as mass, inertia, stiffness) as well as the collisions and contacts automatically detected during motion. To achieve this, objects are provided with actuators capable of generating forces and torques computed via generalized proportional‐derivative controllers. When deflected by external actions, actuated objects try to return to their initial path. Speed variations over time are computed during the simulation, and depend on the complexity of the paths, on the objects models, and on the events such as collisions occurring during motion. In addition simulations are generated at interactive rates, even in the case of complex articulated objects. This facilitates the fine tuning of an animation sequence.

This paper presents an implicit deformable model, based on isosurfaces of potential fields generated by skeletons, that provides elegant and unified formulations for both geometric parameters such as shape or deformation and physical properties such as rigidity.The model is especially designed to improve collision and contact processing for non-rigid objects.In particular, it generates and maintains exact contact surfaces during interactions.

Abstract We propose an integrated set of methods for designing and animating bodies whose deformable flesh coats an articulated skeleton. The proposed methods provide good automatic positioning of the ‘skin’ after movements, and automatic deformation after collisions with rigid or deformable objects (dynamic or static). The response to collisions includes a feedback from the flesh to the skeleton, whose movement is adequately modified. Moreover, coating the skeleton gives an easy solution to closed loop collisions and angle constraints control. Our model is modular and gives some high level control to the user.