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.

We present an extension to traditional rig skinning, like Linear Blend Skinning (LBS), to produce secondary motions that exhibit the appearance of a physical phenomena without need for simulation. At the core of the technique, we call dynamic skinning, is a set of deformers which offset position of individual vertices as a function of position derivatives and time. Examples of such deformers create effects such as oscillation in response to movement and the appearance of wave propagation, among others. Because the technique computes offsets directly and does not solve physics equations, it is extremely fast to compute. It also boasts a highdegree of customizability which supports a desirable artist workflow and fine level of control. Finally, we showcase the technique in a number of scenarios and make comparisons with the state of the art.

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

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.

We present a method for retiming existing 3D animations able to handle seamlessly arbitrary impulse-like user gestures, thus enabling expressive video-based control inspired from common review sessions used in animation studios. The approach works in recording two videos with fast, impulse-based, gestures: one synchronized with the existing 3D animation and another featuring a new time sequence. We then propose an automatic generation of a modified 3D animation retimed to match the sequences of the second video. To this end, we introduce a robust and automatic method relying on Dynamic Time Warping able to compute the sequential correspondence between the timings of the impulse gestures. The method can adapt to various individual gestures without requiring dedicated learning, and can take into account the semantic integrity of the original 3D animation after retiming.

Abstract Biological shapes possess fascinating properties and behaviours that are the result of emergent mechanisms: they can evolve over time, dynamically adapt to changes in their environment, while also exhibiting interesting mechanical properties and aesthetic appeal. In this work, we bring and extend an existing biological‐inspired model of the Physarum polycephalum, aka the blob, to the field of computer graphics, in order to design porous organic‐like microstructures that resemble natural foam‐like cells or filament‐like patterns with variable local properties. In contrast to approaches based on static global optimization that provides only limited expressivity over the result, our method allows precise control over the local orientation of 3D patterns, relative cell extension and precise infill of shapes with well defined boundaries. To this end, we extend the classical agent‐based model for Physarum to fill an arbitrary domain with local anisotropic behaviour. We further provide a detailed analysis of the model parameters, contributing to the understanding of the system behaviour. The method is fast, parallelizable and scalable to large volumes and compatible with user interaction, allowing a designer to guide the structure, erase parts and observe its evolution in real‐time. Overall, our method provides a versatile and efficient means of generating intricate organic microstructures that have potential applications in fields such as additive manufacturing, design or biological representation and engineering.

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 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.

Interactive shape crafting is an increasingly popular feature in video games, offering players a sense of freedom and personalization. In this work, we propose to combine a stochastic simulation approach to solve the heat equation on Implicit Surface, enabling crafting-ready shapes. Our simulation relies on the "Walk on Sphere" (WoS) approach allowing to solve the asymptotic solution of the heat PDE at any point in space without the need for an explicit mesh structure. To enable interactivity when the shape is moved near a heat source, we propose the integration of time-evolving modifiers. Firstly, using the separation of variables over the PDE enables the approximation of the heating evolution using an additional exponential time variation. Then, we procedurally attach local secondary heat sources to the surface for smooth cool-down. We demonstrate the effectiveness our approach on blended-material shapes generated using CSG operations, combining spatially-varying thermal diffusivity. Overall, our method offers a promising avenue for incorporating often-neglected physical interactions, such as heat-related phenomena, into video games with complex and customizable shapes.

Abstract Denoising is a common, yet critical operation in geometry processing aiming at recovering high‐fidelity models of piecewise‐smooth objects from noise‐corrupted pointsets. Despite a sizable literature on the topic, there is a dearth of approaches capable of processing very noisy and outlier‐ridden input pointsets for which no normal estimates and no assumptions on the underlying geometric features or noise type are provided. In this paper, we propose a new robust‐statistics approach to denoising pointsets based on line processes to offer robustness to noise and outliers while preserving sharp features possibly present in the data. While the use of robust statistics in denoising is hardly new, most approaches rely on prescribed filtering using data‐independent blending expressions based on the spatial and normal closeness of samples. Instead, our approach deduces a geometric denoising strategy through robust and regularized tangent plane fitting of the initial pointset, obtained numerically via alternating minimizations for efficiency and reliability. Key to our variational approach is the use of line processes to identify inliers vs. outliers, as well as the presence of sharp features. We demonstrate that our method can denoise sampled piecewise‐smooth surfaces for levels of noise and outliers at which previous works fall short.

Cartoon effects described in animation principles are key to adding fluidity and style to animated characters. This paper extends the existing framework of Velocity Skinning to use skeletal acceleration, in addition to velocity, for cartoon-style effects on rigged characters. This Acceleration Skinning is able to produce a variety of cartoon effects from highly efficient closed-form deformers while remaining compatible with standard production pipelines for rigged characters. The paper showcases the introduction of the framework along with providing applications through three new deformers. Specifically, a followthrough effect is obtained from the combination of skeletal acceleration and velocity. Also, centrifugal stretch and centrifugal lift effects are introduced using rotational acceleration to model radial stretching and lifting. The paper also explores the application of effect-specific time filtering when combining deformations together allowing for more stylization and artist control over the results.

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.

Tensor fields are useful for modeling the structure of biological tissues. The challenge to measure tensor fields involves acquiring sufficient data of scalar measurements that are physically achievable and reconstructing tensors from as few projections as possible for efficient applications in medical imaging. In this paper, we present a filtered back-projection algorithm for the reconstruction of a symmetric second-rank tensor field from directional X-ray projections about three axes. The tensor field is decomposed into a solenoidal and irrotational component, each of three unknowns. Using the Fourier projection theorem, a filtered back-projection algorithm is derived to reconstruct the solenoidal and irrotational components from projections acquired around three axes. A simple illustrative phantom consisting of two spherical shells and a 3D digital cardiac diffusion image obtained from diffusion tensor MRI of an excised human heart are used to simulate directional X-ray projections. The simulations validate the mathematical derivations and demonstrate reasonable noise properties of the algorithm. The decomposition of the tensor field into solenoidal and irrotational components provides insight into the development of algorithms for reconstructing tensor fields with sufficient samples in terms of the type of directional projections and the necessary orbits for the acquisition of the projections of the tensor field.

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 propose a method leveraging the naturally time-related expressivity of our voice to control an animation composed of a set of short events. The user records itself mimicking onomatopoeia sounds such as ”Tick”, ”Pop”, or ”Chhh” which are associated with specific animation events. The recorded soundtrack is automatically analyzed to extract every instant and types of sounds. We finally synthesize an animation where each event type and timing correspond with the soundtrack. In addition to being a natural way to control animation timing, we demonstrate that multiple stories can be efficiently generated by recording different voice sequences. Also, the use of more than one soundtrack allows us to control different characters with overlapping actions.

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.

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.

We propose an efficient method to model paper tearing in the context of interactive modeling. The method uses geometrical information to automatically detect potential starting points of tears. We further introduce a new hybrid geometrical and physical-based method to compute the trajectory of tears while procedurally synthesizing high resolution details of the tearing path using a texture based approach. The results obtained are compared with real paper and with previous studies on the expected geometric paths of paper that tears.

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 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 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 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.

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.

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 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.