Search

A practical technique is presented for efficiently rendering oriental black ink paintings with realistic diffusion effects, being based on models which simulate a variety of paper types and black ink properties. Strokes can be generated by bristles or elastic brush models simulating those actually used in oriental black ink painting. Incorporation of paper modeling allows users to draw on a wide variety of papers having either randomly generated fiber meshes or uniform meshes commonly found in fabrics which are also frequently used. This accordingly provides a unique platform for real-time dynamic simulation of realistic ink diffusion in that the resultant diffusion images reflect the texture and the global change of gray tones as well as local temporal variations specific to a particular paper. Examples are presented demonstrating the capability of the proposed technique for handling different ink and paper properties.

This paper proposes a novel technique for converting a given animated mesh into a series of displaced subdivision surfaces. Instead of independently converting each mesh frame in the animated mesh, our technique produces displaced subdivision surfaces that share the same topology of the control mesh and a single displacement map. We first propose a conversion framework that enables sharing the same control mesh topology and a single displacement map among frames, and then present the details of the components in the framework. Each component is specifically designed to minimize the shape conversion errors that can be caused by enforcing a single displacement map. The resulting displaced subdivision surfaces have a compact representation, while reproducing the details of the original animated mesh. The representation can also be used for efficient rendering on modern graphics hardware that supports accelerated rendering of subdivision surfaces.

Classical (or biaxial) twill is a textile weave in which the weft threads pass over and under two or more warp threads, with an offset between adjacent weft threads to give an appearance of diagonal lines. This paper introduces a theoretical framework for constructing twill-woven objects, i.e., cyclic twill-weavings on arbitrary surfaces, and it provides methods to convert polygonal meshes into twill-woven objects. It also develops a general technique to obtain exact triaxial-woven objects from an arbitrary polygonal mesh surface.

In this paper, we present a new algorithm for quad-dominant meshing of unorganized point clouds based on periodic global parameterization. Our meshing method is guided by principal directions so as to preserve the intrinsic geometric properties. We use local Delaunay triangulation to smooth the initial principal directions and adapt the global parameterization to point clouds. By optimizing the fairness measure we can find the two scalar functions whose gradients best align with the guided principal directions. To handle the redundant vertices in the iso-lines due to overlapped triangles, an approach is specially designed to clean the iso-lines. Our approach is fully automatic and applicable to a surface of arbitrary genus. We also show an application of our method in curve skeleton extraction from incomplete point cloud data.

Modeling of realistic garments is essential for creating believable virtual environments. Sketch-based modeling of garments presents an appealing, easy to use alternative to the established modeling approaches which are time consuming and require significant tailoring expertise. Unfortunately, the results created using existing sketch-based methods lack realism. Driven by human perception of garment sketches, we propose a context-aware garment sketch interpretation based on a set of observations about key factors that affect the shape of garments. Based on this analysis we develop a geometric method for sketch-based modeling of garments which obtains more realistic results than previous techniques. We demonstrate the effectiveness of our method on a variety of inputs and validate our approach via a user study where viewers were asked to compare the believability of our outputs versus previous ones.

We introduce a surface reconstruction algorithm suitable for large point sets. The algorithm is an octree-based version of the Cocone reconstruction algorithm [4], allowing independent processing of small subsets of the total input point set. When the points are sufficiently sampled from a smooth surface, the global guarantee of topological correctness of the original algorithm is preserved, together with the geometric accuracy guarantees.

Folding a thin sheet material such as paper along curves creates a developable surface composed of ruled surface patches. When using such surfaces in design, designers often repeat a process of folding along curves drawn on a sheet and checking the folded shape. Although several methods for constructing such shapes on a computer have been proposed, it is still difficult to check the folded shapes instantly from the crease patterns. In this paper, we propose a simple method that approximately realizes a simulation of curved folds with a triangular mesh from its crease pattern. The proposed method first approximates curves in a crease pattern with polylines and then generates a triangular mesh. In order to construct the discretized developable surface, the edges in the mesh are rearranged so that they align with the estimated rulings. The proposed method is characterized by its simplicity and is implemented on an existing origami simulator that runs in a web browser.

Although 3D Voronoi diagrams and medial axis transforms have numerous applications in biology, robotics, and manufacturing, most researchers use Voronoi diagrams of points instead of the true 3D input geometry, due to issues of robustness and scalability. In this paper, we present a robust sample-based GPU algorithm for calculating the full topology of Voronoi diagrams of non-general position spheres. Prior work demonstrated that the presence, geometry, and combinatorial basis of spheres that contribute to Voronoi vertices can be efficiently computed by shooting rays from each input sphere, mapping ray intersections with the nearest bisector surface to parametric bounding cubes, and analyzing the results. In this paper, we propose an algorithm on this parametric bounding cube to compute Voronoi edges in addition to the vertices. We successfully extract the full topology of the Voronoi diagram, including special cases such as isolated Voronoi edges that do not contain Voronoi vertices, more than three Voronoi edges emanating from a Voronoi vertex, and Voronoi edges that are shared by more than three Voronoi cells. Our GPU implementation efficiently and robustly handles all input, whether in general or non-general position, and finds all Voronoi vertices and edges, modulo the sampling density, including isolated disconnected edges.

This paper proposes a hybrid Lagrangian–Eulerian method involving all participating media for high-speed fluid simulation and its accompanying phenomena. We take advantages of both particle- and grid-based solvers in our new approach by dividing all the physical states into two different parts based on their individual characteristics. Lagrangian-based solver gives rise to liquid, droplet, and foam creation and facilitates the drastic shape distortion and state transition during the multi-physical processes simulation from the perspective of individual particles. At the same time, Eulerian-based solver mainly focuses on the animation of spray, which enables a fog-like atmosphere. Essential to all of the aforementioned functionalities is the state transition among different media considering both physical and geometric features in this paper. The state transition enables to streamline the dis-association and generation of certain physical states. Moreover, to ensure the synchronization of hybrid models, we establish essential interaction and build tight coupling between the particle- and grid-based subsystems. With the comprehensive experimental results, we have manifested that our new modeling approach is both effective and highly modularized, and is capable of producing convincing visual effects for a wider range of graphics and animation tasks.

Object skeleton is a useful geometric tool for shape analysis tasks. It encodes the topological structure of the primitive shape and preserves a geometric cue as well. Skeletonization is a seemingly simple but difficult research problem. A desirable skeletonization algorithm has to be topologically complete, insensitive to boundary noise, without any branch pruning and free of user-specified parameters. In this paper, we propose a novel method based on the heat equation to extract skeletons assuming that the input is a binary image. Based on the connection between the skeleton and ridge lines, we use the smooth heat diffusion height surface to approximate the real distance field, and then extract the ridge lines of the surface as the output skeleton. Different from the existing approaches, the proposed method in this paper has the above-mentioned excellent properties and can capture the clean and stable skeleton directly. Extensive experimental results show that the new approach can yield better skeletons than the state-of-the-art.

The animation of articulated characters is a central problem in the computer graphics field. Skeletal animation techniques define a workflow which has proven to be effective for boundary representations (B-Reps). This paper extends the classical skeletal animation pipeline to deal with characters internal tissues. In contrast to most common approaches, the proposed technique automates all the stages of this workflow. Well known skinning algorithms, such as Linear Blending Skinning, Dual Quaternion Skinning or Optimized Centers of Rotation were adapted to allow the use of our technique in applications where interactivity is required. The pipeline proposed in this paper can be used in many computer graphics systems such as games or educational applications to visualize and animate the internal anatomy of a virtual character at interactive rates.

In this paper, we present a new piecewise parametric approach to obtain smooth surfaces from any given orientable 2-manifold polynomial control mesh. Our approach provides C 2 continuous Bi-Cubic Bezier patches that are guaranteed to be stitched with G 1 continuity regardless of the underlying mesh topology. A high level summary of the approach can be given as a two-step process: (1) Starting from an orientable 2-manifold mesh we apply vertex-insertion, which is remeshing algorithm of Catmull–Clark subdivision, to break that surface into a set of all quadrilateral patches. (2) for each such quadrilateral patch, we construct a Bi-Cubic Bezier patch, where the positions of the 16 control points are obtained from the limit surface of the Doo–Sabin subdivision scheme. This approach, when combined with topological modeling, provides a framework for real-time interactive modeling of smooth manifold meshes with arbitrary topology. Based on this approach, we have developed an interactive modeling system that allows users to work with smooth surfaces in real-time by opening or closing holes, creating handles, and combining and disconnecting surfaces. The paper has three main contributions: (1) We guarantee that our method will produce only smooth manifold meshes with C 2 continuous Bi-Cubic Bezier patches. (2) We guarantee visual smoothness for any arbitrary topological structure by providing geometric G 1 continuity in boundaries of patches. (3) We demonstrate that smooth surfaces with arbitrary topology can be created interactively in real-time using parametric patches.

This paper presents a direct stylization system to render 3D animated geometry as watercolor painted animation. Featuring low-level art-direction in real-time, our approach focuses on letting users paint custom stylization parameters in the 3D scene. These painted parameters drive watercolor effects in object-space, managing localized control and emulating the characteristic appearance of traditional watercolor. For this purpose, the parameters alter the object-space geometric representations and are rasterized, to coherently control and enhance further image-space effects. The watercolor effects are simulated through improved and novel algorithms to recreate hand tremors, pigment turbulence, color bleeding, edge darkening, paper distortion and granulation. All these represent essential characteristic effects of traditional watercolor. The proposed direct stylization system scales well with scene complexity, can be implemented in most rendering pipelines and can be adapted to simulate a wide range of watercolor looks. The simulation is compared to previous approaches and is evaluated through a user study, involving professional CG artists spending over 50 h stylizing their own assets and sharing their feedback about the watercolor stylization, the direct stylization system and their needs as artists using Non-photorealistic Rendering (NPR). Accepted version

This paper discusses the creation of star effects in captured night-time photos based on using depth information available by stereo vision. Star effects are an important design factor for night-time photos. Modern imaging technologies support that night-time photos can be taken free-hand, but star effects are not achievable for such camera settings. Self-calibration is an important feature of the presented star-effect simulation method. A photographer is assumed to take just an uncalibrated stereo image pair (i.e. a base and a match image), for example by taking two photos subsequently (e.g. by a mobile phone at about the same pose). For self-calibration we apply the following routine: extract a family of pairs of feature points, calibrate the stereo image pair by using those feature points, and calculate depth data by stereo matching. For creating the star effects, first we detect highlight regions in the base image. Second, we estimate the luminance according to available depth information. Third, we render star patterns with a chosen input texture. Basically we provide a complete tool which is easy to apply for the generation of a user-selected star texture. Minor variations can be introduced in star pattern rendering in order to achieve more natural and vivid looking star effects. By extensive experiments we verified that our rendering results are potentially similar to real-world star effect photos. We demonstrate some of our results, also for illustrating that they appear more natural than results achieved by existing commercial applications. We also illustrate that our method allows us to render more artistic star patterns not available in recorded photographs. In brief, this paper reports research on automatically simulating both photorealistic and non-photorealistic star effects.

Folding planar sheets to make 3D shapes from is an ancient practice with many new applications, ranging from personal fabrication of customized items to design of surgical instruments for minimally invasive surgery in self-folding machines. Given a polyhedral mesh, unfolding is an operation of cutting and flattening the mesh. The flattened polyhedral nets are then cut out of planar materials and folded back to 3D. Unfolding a polyhedral mesh into planar nets usually require segmentation. Either used as a preprocessing step to simplify the mesh and provide semantics or as the result of unfolding to avoid overlapping, the segmentation and the unfolding operations are decoupled. Consequently, segmented components may not be unfoldable and unfolded nets usually provide no semantic meaning and make folding difficult. In this paper, we propose a strategy that tightly couples unfolding and segmentation. We show that the proposed method produces unfoldable segmentation that resembles carefully designed paper craft. The key idea that enables this capability is an algorithm that learns from failed unfoldings. Graphical abstractDisplay Omitted HighlightsWe propose a strategy that produces unfoldable segmentation via failed unfoldings.Our unfoldable segmentation provides shape semantics and convexity.Shape semantics in the proposed segmentation eases the fabrication process.High convexity allows higher proability of finding collision-free folding path.Collision-free folding path is critical in developing a self-folding machine.

Mesh saliency was introduced and joined the community of computer graphics ten years ago, which can benefit various applications, for instance, mesh reduction, mesh segmentation, self-similarity matching, scan integration, volume rendering, 3D printing, etc. Before, saliency detection had been successfully applied to image processing and pattern recognition to study how the world is perceptually intelligible for robots. In contrast to color of images and coherence of videos, geometric signals are defined with two-dimensional manifolds whose discrete representation is irregular, leading differences to the nature and difficulties to the solution of mesh saliency. To tackle the challenge, the last decade has witnessed significant advances in mesh saliency detection. However, a survey of recent advances in mesh saliency detection as well as its applications does not yet exist to date. This paper provides a first and comprehensive reference source of shape context based mesh saliency for researchers from a wide range of domains, including but not limited to computer graphics and vision. It reviews main contributions, advantages, drawbacks, and applications of known mesh saliency detection methods and discusses current trends and outlook for future study. Graphical abstractDisplay Omitted HighlightsThe paper provides the first and comprehensive reference resource of mesh saliency.35 representative methods published from 2005 to 2015 are viewed.4 key insights into the topic are presented, and open problems are raised.

Indirect illumination is an essential part of realistically rendering virtual scenes. In this paper we present a new method for computing multi-bounce indirect illumination for diffuse surfaces which is particularly well-suited for indoor scenes with complex occlusion, where an appropriate simulation of the indirect illumination is extremely important. The technique presented in this paper combines the benefits of shooting methods with the concept of photon mapping to compute a convincing light map for the scene with full diffuse lighting effects. The main idea is to carry out a multi-bounce light distribution almost entirely on the GPU using a shooting approach with virtual point lights. The final result is then stored in a texture atlas by projecting the energy from each virtual point light into the texels visible from its perspective. The technique uses only few resources on the graphics card and is flexible in the sense that it can easily be adjusted for either quality or speed, allowing the user to create convincing results in a matter of seconds or minutes, depending on the scene complexity. Graphical abstractDisplay Omitted HighlightsApproximating a physically correct light distribution with multiple bounces.Developing a progressive refinement algorithm for virtual point lights on the GPU.Creating a high-resolution light atlas with a special projection method on the GPU.

A stencil is a thin sheet of material, such as paper, plastic, or metal, with certain patterns cut from it. Applying a pigment through the cut-out holes produces a design on an underlying surface. Using multiple overlapping stencil layers, artists can create intricate, yet reproducible imagery on a variety of surfaces. Traditionally, artists have to design not only the final appearance, but also each individual stencil layer. A stencil layer needs to be connected, geometrically simple, and physically stable. Taking all these constraints into account during the design process is difficult and unintuitive even for skilled artists.In this paper, we propose a system which separates the artistic design stage from the complex and tedious task of stencil creation. For a given user design, our algorithm automatically generates a set of stencil layers satisfying all required properties. The task is formulated as a constrained energy optimization problem and solved efficiently. Experiments, including a user study, are carried out to examine the complete algorithm as well as each individual step. Graphical abstractDisplay Omitted HighlightsOur approach for stencil creation is capable of handling multiple layers.The layer segmentation is optimized while enforcing the stencil?s topology constraints.The layer ordering is optimized to reduce the need to add bridges.A physical simulation of the stencil?s stability helps to produce applicable stencils.An interactive website allows exploring different artistic options.

Smoke control involves shape and path. A unified framework able to deal with both of them will enable animators to manipulate the shape and path of smoke animation more effectively. In this paper, we develop such a unified framework. With our approach, path control, shape control, and mixed control of both can be handled satisfactorily in the same framework. In order to develop this framework, we use a signed distance field to provide three control forces: path control force, boundary control force, and shape control force based on medial axis point clouds. The path control force makes the smoke move along the appointed route, the boundary control force keeps the smoke moving through specified regions only, and the shape control force enables the smoke to form various given shapes. The boundary control force and the shape control force are two novel control forces developed in this paper. To make the smoke form the target shape more accurately, we develop an adaptive strategy to adjust the divergence field. We also employ a new hybrid vortex particle scheme to enhance the turbulence flow details. The examples given in this paper indicate that our proposed framework is advantageous over the existing shape control approaches and path control algorithms, and a naive combination of the two.

Morphological shape design is interpreted in this paper as a search for new shapes from a particular application domain represented by a set of selected shape instances. This paper proposes a new foundation for morphological shape design and generation. In contrast to existing generative procedures, an approach based on a user-controlled metamorphosis between functionally based shape models is presented. A formulation of the pairwise metamorphosis is proposed with a variety of functions described for the stages of deformation, morphing and offsetting. This formulation is then extended to the metamorphosis between groups of shapes with user-defined, dynamically correlated and weighted feature elements. A practical system was implemented in the form of plugin to Maya and tested by an industrial designer on a group of representative shapes from a particular domain. © 2013 Elsevier Ltd.

International audience; To capture the real-world luminance values, High Dynamic Range (HDR) image processing has been developed. HDR images have a richer content than the widely-used Standard Dynamic Range (SDR) images, and are used in a number of situations, e.g. in film industry. As HDR displays are more and more commercially available, we need to be able to process HDR images as well as SDR ones (for example, devising denoising algorithms, inpainting or anti-aliasing). The most powerful methods to process images are now deep neural networks. However, the training of such networks calls for a lot of images, and HDR images datasets are relatively small.One way to generate HDR images is inverse tone mapping operators (iTMOs). They are algorithms that expand the dynamic range of SDR images. In this paper, we propose HDR-LFNet, a novel iTMO, and its HDR training dataset. Our method merges several existing handcrafted iTMOs, combined in a supervised neural network to produce an HDR output. Our lightweight network requires less training images than state-of-the-art methods, and has faster training phase. Besides, the quality of the generated images is similar to the state-of-the-art. We present the architecture as well as the subjective and experimental evaluations of our method.

In a recent paper (Ma and Wang, 2009), it was found that the limit curve corresponding to a regular edge path of a Loop subdivision surface reduces to a uniform cubic B-spline curve (CBSC) under a degeneration condition. One can thus define a Loop subdivision surface interpolating a set of input CBSCs with various topological structures that can be mapped to regular edge paths of the underlying surface. This paper presents a new solution for defining a Loop subdivision surface interpolating an arbitrary number of CBSCs meeting at an extraordinary point. The solution is based on the concept of a polygonal complex method previously used for Catmull-Clark surface interpolation and is built upon an extended set of constraints of the control vertices under which local edge paths meeting at an extraordinary point reduces to a set of endpoint interpolating CBSCs. As a result, the local subdivision rules near an extraordinary point can be modified such that the resulting Loop subdivision surface exactly interpolates a set of input endpoint interpolating CBSCs meeting at the extraordinary point. If the given endpoint interpolating CBSCs have a common tangent plane at the meeting point, the resulting Loop surface will be G^1 continuous. The proposed method of curve interpolation provides an important alternative solution in curve-based subdivision surface design.

CAD mesh models have been widely employed in current CAD/CAM systems, where it is quite useful to recognize the features of the CAD mesh models. The first step of feature recognition is to segment the CAD mesh model into meaningful parts. Although there are lots of mesh segmentation methods in literature, the majority of them are not suitable to CAD mesh models. In this paper, we design a mesh segmentation method based on clustering, dedicated to the CAD mesh model. Specifically, by the agglomerative clustering method, the given CAD mesh model is first clustered into the sparse and dense triangle regions. Furthermore, the sparse triangle region is separated into planar regions, cylindrical regions, and conical regions by the Gauss map of the triangular faces and Hough transformation; the dense triangle region is also segmented by the mean shift operation performed on the mean curvature field defined on the mesh faces. Lots of empirical results demonstrate the effectiveness and efficiency of the CAD mesh segmentation method in this paper.

Image textures can easily be created using texture synthesis by example. However, creating procedural textures is much more difficult. This is unfortunate, since procedural textures have significant advantages over image textures. In this paper we address the problem of texture synthesis by example for procedural textures. We introduce a method for procedural multiresolution noise by example. Our method computes the weights of a procedural multiresolution noise, a simple but common class of procedural textures, from an example. We illustrate this method by using it as a key component in a method for texture synthesis by example for isotropic stochastic procedural textures. Our method significantly facilitates the creation of these procedural textures. Graphical AbstractIn this paper, we present a method for texture synthesis by example for procedural isotropic stochastic textures. Our method is illustrated in the example, which shows a photograph of a real-world scene, a photograph of a texture in the scene, a cropped version of the photograph of the texture, a procedural texture automatically generated from the cropped version of the photograph using our method, and a rendering of a virtual scene textured using several of these procedural textures.Display Omitted Research Highlights? Stochastic textures are well reproduced by matching the power spectrum and the histogram in a decorrelated color space. ? The weights of a procedural multiresolution noise can be computed from an exemplar using a simple direct method. ? Unsuccessfully synthesized textures are often still usable at a low level of detail or in a preattentive context.

An essential prerequisite to construct a manifold trihedral polyhedron from a given natural (or partial-view) sketch is solution of the ''wireframe sketch from a single natural sketch (WSS)'' problem, which is the subject of this paper. Published solutions view WSS as an ''image-processing''/''computer vision'' problem where emphasis is placed on analyzing the given input (natural sketch) using various heuristics. This paper proposes a new WSS method based on robust tools from graph theory, solid modeling and Euclidean geometry. Focus is placed on producing a minimal wireframe sketch that corresponds to a topologically correct polyhedron.

In this paper, we propose a new region-growing based iso-surface extraction algorithm that can generate high-quality curvature-adaptive semi-regular meshes, preserve sharp features and will extract all the disjoint components of the iso-surface. More importantly, in this paper, we propose a novel normal consistency constraint that ensures the intersection of the Delaunay sphere of the new triangle and the iso-surface is a topological disk, an important property that makes the new algorithm very robust when dealing with large scale of volumetric datasets of complex topology and geometry.

This paper explores a new family of 2D interpolating subdivision schemes that calculate subdivision points from tangent specifications. In this approach each level of subdivision drives the curve toward its specified tangents. The paper describes the underlying algorithmic formulation, and outlines a number of variations, which differ in how subdivision points are computed from tangents or in how tangents are derived. The different characteristics of these variations are shown to provide an interesting range of shapes, giving a high degree of artistic control. Each variation is shown to guarantee C1 continuity except for special identifiable cases, and some of these variations can produce circles. A number of examples are explored that demonstrate the power of the approach as a modeling tool for constructing complex curves, and a comparison is made with curves produced by the Kobbelt subdivision scheme.

This paper presents a scheme for decomposing polygons called multi-L-REP. The scheme can be considered as a generalization of the L-REP decomposition, which associates the edges of a polygon with a set of layered triangles. In the multi-L-REP these layered triangles are grouped into regions of a plane division. The paper also shows some alternative algorithms for its construction, and one of its applications: the point-in polygon inclusion test. Finally, a special case of multi-L-REP that has several interesting properties and shows a very fast point-in-polygon inclusion test is presented.

In this paper the problems of user interaction in a mobile environment are investigated. Interaction in this environment imposes new requirements both on UI designers and the users. This paper deals in particular with problems of graphical interaction in a mobile environment. The interaction in a mobile environment requires new approaches that will result in a new type of rendering of graphical data. A rendering technique that enables rendering and annotation of objects in a 3D scene on mobile devices is presented. This technique is based on transformation of the 3D scene to a 2D vector graphic representation. The input 3D scene is given in the VRML format and the output 2D format is SVG. In the second part of this paper we are presenting a prototype of a voice user interface that allows users to interact with the graphical data in a mobile environment. The semantic description of the scene plays the key role in restriction of the language used for communication. The communication between the user and the mobile system is performed by means of natural language that is restricted according to the context the user is currently in. The implementation of the voice user interface is based on the existing VoiceXML platform.

The paper presents two applications of haptic technologies to demonstrate how they can increase human computer interaction during different steps of design process. The first application aims at developing a system to generate digital shapes by manipulating haptic tools that resemble the physical ones that the modelers use in everyday work. The second is focused on the use of haptic interfaces to evaluate ergonomics of virtual products control boards. We designed and developed the mentioned haptic devices; the first uses two FCS HapticMaster equipped with a innovative strong and stiff 6 DOF device carrying simulated clay modeling tools. The second is an ''ad hoc'' mechatronic device able to simulate some controls with rotary motions (knobs). The described haptic devices are integrated in more complex virtual reality applications; the paper describes their architecture and the methodologies proposed to simulate material shaping and ergonomic validation. The main aspects of haptic modeling and rendering are also discussed.

Instance segmentation is an essential part of image semantic understanding. In this paper we propose a novel cascade framework for instance segmentation. Unlike some existing methods that only output contour discrete coordinates, our approach obtains a vectorized representation of contours using periodic B-splines. In order to make better use of geometry and appearance information, we consider the global and local features of objects and introduce two types of graph structures, the star graph and circular graph, for feature extraction. Thereby, we develop a neural network, termed the mix network, to better exploit extracted features. Specifically, we first regress the spline control points to an object boundary via the mix network, then perform spline sampling to obtain the initial predictions of contours, and finally deform the predicted contours to the real contours of the objects. In addition, we add a regularization to further constrain the fairness of contour splines. Experiments show that our approach achieves 34.6% in mask mAP, Mean Average Precision, with a ResNet-101-FPN-DCN backbone on the challenging COCO benchmark, which significantly improves the performance of contour-based methods.

The electrovibration tactile display could render the tactile feeling of different textured surfaces by generating the frictional force through voltage modulation. When a user is sliding his/her finger on the display surface, he/she can feel the frictional texture. However, it is not trivial to prepare and fine-tune the appropriate frictional signals for haptic design and texture simulation. In this paper, we present a deep-learning-based framework to generate the frictional signals from the textured images of fabric materials. The generated frictional signal can be used for the tactile rendering on the electrovibration tactile display. Leveraging GANs (Generative Adversarial Networks), our system could generate the displacement-based data of frictional coefficients for the tactile display to simulate the tactile feedback of different fabric materials. Our experimental results show that the proposed generative model could generate the frictional-coefficient signals visually and statistically close to the ground-truth signals. The following user studies on fabric-texture simulation show that users could not discriminate the generated and the ground-truth frictional signals being rendered on the electrovibration tactile display, suggesting the effectiveness of our deep-frictional-signal-generation model.

Skeleton creation is an important phase in the character animation pipeline. However, handcrafting skeleton takes extensive labor time and domain knowledge. Automatic skeletonization provides a solution. However, most of the current approaches are far from real-time and lack the flexibility to control the skeleton complexity. In this paper, we present an efficient skeletonization method, which can be seamlessly integrated into the sketch-based modeling process in real-time. The method contains three steps: local sub-skeleton extraction; sub-skeleton connection; and global skeleton refinement. Firstly, the local skeleton is extracted from the processed polygon stroke and forms a subpart along with the sub-mesh. Then, local sub-skeletons are connected according to the intersecting relationships and the modeling sequence of subparts. Lastly, a global refinement method is proposed to give users coarse-to-fine control on the connected skeleton. We demonstrate the effectiveness of our method on a variety of examples created by both novices and professionals., Shape Modeling International 2021

In this paper a pen-based intuitive interface is presented, that controls a virtual human figure interactively. Recent commercial pen devices can detect not only the pen positions but also the pressure and tilt of the pen. We utilize such information to make a human figure perform various types of motions in response to the pen movements manipulated by the user. The figure walks, runs, turns and steps along the trajectory and speed of the pen. The figure also bends, stretches and tilts in response to the tilt of the pen. Moreover, it ducks and jumps in response to the pen pressure. Using our interface, the user controls a virtual human figure intuitively as if he or she were holding a virtual puppet and playing with it. In addition to the interface design and implementation, this paper describes a motion generation engine to produce various motion based on varying parameters that are given by the pen interface. We take a motion blending approach and construct motion blending modules with a set of small number of motion capture data for each type of motions. Finally, we present the results from user experiments and comparison with a transitional gamepad-based interface.

Real-time rendering of pixel-accurate hard shadows in 3D scenes is still a challenging problem for shadow generation techniques. In this paper, we present the concept of non-overlapping geometric shadow map (NOGSM), which enables the construction of high-quality hard shadows from static lights for any point in the scene. The NOGSM is created in a preprocessing phase, in which the scene’s geometry is looked at from the light’s point of view. All hidden surfaces are removed through total elimination of hidden polygons plus clipping of the partially hidden polygons. The resulting list of non-overlapping projected polygons is then stored in a multi-grid data structure. Our solution generates shadows with far better quality than standard shadow mapping techniques, while maintaining real time performance, and using a smaller memory footprint than compression techniques.

3D CAD models play an important role in large-scale engineering projects. The increasing demand for highly-detailed datasets presents a challenge for efficient storage, transmission, and rendering. To reduce dataset size, 3D shape matching techniques have been proposed to find repeated triangle meshes, but are strongly dependent on surface triangulation. Meanwhile, existing shape registration techniques are not well suited for the 3D CAD domain. In this paper, we present a deep learning-based framework that uses point clouds to identify repeated instances of triangle meshes (a single 3D CAD model component) overcoming the limitations of previous work and guaranteeing an upper bound on any geometric errors. The framework combines PointNet++ for shape classification with a registration procedure based on Principal Component Analysis and the Adam optimizer. The resulting affine transformation can be used to efficiently instantiate repeated CAD geometries. Using the proposed framework, we were able to reduce a real-world 3D CAD model to 2.61% of its original size, while preserving its geometric accuracy and improving rendering performance.

This paper presents a progressive algorithm by which we can narrow down the searching domain for face identification and reconstruct various 3D objects from a single freehand line sketch drawing in short time. The sketch drawings served as an input for the reconstruction process in this paper are obtained from an inaccurate freehand sketch of a 3D wireframe object, which is the edge–vertex graph without any removal of hidden lines. The algorithm is executed through two stages. First, at the face identification stage, every possible faces are generated from the sketch and they are classified into implausible faces, basis faces and minimal faces by means of the geometrical and topological constraints in order to reduce the searching space. The proposed algorithm searches minimal space of the faces so that the actual faces of the given object could be identified in short time. Second, at the object reconstruction stage, we calculate a 3D structure progressively by optimizing the vertices coordinates of the object in accordance with the sketching order of faces. This progressive method reconstructs the most plausible 3D object in a short time by applying the 3D constraints that are derived from the relationship between an object and its sketch drawing in the optimization process. In addition, this method makes it possible for designers to change their viewpoints while sketching. In this paper, we are describing the progressive reconstruction algorithm, and giving the results of the implementation.

Panoramic imaging has important implications in robotics, computer vision and virtual reality. This paper reviews representative work in the design and development of 2D/3D panoramic image capturing systems, the advancement of auto-calibration, registration and corresponding techniques, stereo vision, 3D reconstruction and image-based rendering. The paper discusses the above work within four parts of the panoramic imaging process: capturing system, image processing for panoramic imaging, image stitching and 3D reconstruction, image-based rending and visualisation. The design and development of a panoramic system pays careful attention to the following issues: image capturing, image registration, camera calibration, feature extraction, image understanding and image stitching. The objective of this review paper is to summarise and compare some of the methods in the various stages and identify research topics and applications, which are at the forefront of this exciting and challenge field.

This paper presents a sketch-based mesh extrusion method, which is useful for intuitive, efficient geometric modeling of freeform polygonal objects. With our method, the user can extrude either a closed or open surface from the surface or the boundary of a given mesh by sketched input. Thus, compared to earlier methods, our method provides more flexibility for solving surface modeling problems. Our mesh extrusion algorithm consists of four steps: (1) create a base curve; (2) project extruding strokes; (3) sweep a base curve; and (4) sew adjacent curves. At the end of this paper, examples of our mesh extrusion implementation are shown to demonstrate its functionality. Our freeform extrusion has been implemented as a part of our sketch-based modeling system, and the mesh extrusion can be completed in real time on a standard PC.

This paper proposes a mesh simplification algorithm using a discrete curvature norm. Most of the simplification algorithms are using a distance metric to date. The distance metric is very efficient to measure geometric error, but it is difficult to distinguish important shape features such as a high-curvature region even though it has a small distance metric. We suggest a discrete curvature norm to measure geometric error for such features. During simplification the new vertex resulted from an edge collapse takes a position using a butterfly subdivision mask to minimize geometric error. This paper shows that simplification results have smaller geometric errors than previous works, when a discrete curvature norm anda d istance metric are together appliedto its criterion. r 2002 Publishedby Elsevier Science Ltd .

Volume segmentation based on surface attributes is an essential problem in multi-material fabrication and model packing. In practice, current mainstream fabrication techniques have difficulties in yielding models with diverse surface attributes in one pass owing to their craft limitations, making model segmentation a sensible choice for model realization. Partitioning 3D objects into single-attribute volumetric parts prevents fabricating models with different material in a single printing procedure, whereas the arisen challenge is to determine a reliable segmentation solution that is able to handle complicated models in various use scenarios. To achieve this goal, we propose a novel volume partition algorithm generating feasible volumetric parts, each of which is affiliated with one single surface attribute. Our technique enables model segmentation with least conflict and constrained wall thickness so that each volumetric segment can be realized independently by 3D-printing. Generally, it starts with computing a partition proposal guided by radial-based-function iso-surface, then optimizes segmentation interface with a prescribed minimal printing thickness to produce high-quality surface for every volumetric part, and finally splits unextractable volumetric parts into smaller sub-volumes to ensure assemblability of the whole model. As previous methods do not work well in optimizing segment interface for printing, we propose a differential evolution based smoothing algorithm to generate smooth and continuous interface, declining the risk of collision between adjacent volumetric parts. Extensive experimental results are provided in this paper to demonstrate the effectiveness and quality of our proposed technique, showing its advantages on model manufacture over prior methods.

Motion Blur is an important effect of photo-realistic rendering. Distribution ray tracing can simulate motion blur very well by integrating light, both over the spatial and the temporal domain. However, increasing the problem by the temporal dimension entails many challenges, particularly in cinematic multi-bounce path tracing of complex scenes, where heavy-weight geometry with complex lighting and even offscreen elements contribute to the final image. In this paper, we propose the Motion DAG (Directed Acyclic Graph), a novel data structure that filters an entire animation sequence of an object, both in the spatial and temporal domain. These Motion DAGs interleave a temporal interval binary tree for filtering time consecutive data and a sparse voxel octree (SVO), which simplifies spatially nearby data. Motion DAGs are generated in a pre-process and can be easily integrated in a conventional physically based path tracer. Our technique is designed to target motion blur of small objects, where coarse representations are sufficient. Specifically, in this scenario our results show that it is possible to significantly reduce both, memory consumption and render time.

In this paper, we provide formal definitions for object space, space subdivision and ray tracing. We also introduce concept models such as ordered space subdivisions and ordered visualization. From these works, we can evaluate the correctness and performance of our space subdivision scheme for volume visualization. With these definitions, we also analyze some established space subdivision approaches such as uniform space subdivision and octree based space subdivision. In this paper, we suggest a new subdivision strategy, the convex object based subdivision scheme, which can be more efficient in generating the convex objects for ordered visualization.

In this paper we propose a new mesh watermarking scheme for triangle meshes, which are widely used in computer graphics systems. Arbitrary meshes lack a natural parameterization for frequency-based signal processing, and thus they are harder to be watermarked. In this paper, we adopt Guskov’s multiresolution signal processing method for meshes and use his 3D non-uniform relaxation operator to construct a Burt–Adelson pyramid for the mesh, and then watermark information is embedded into a suitable coarser mesh. Since all the computation and data structures are the same as those used in the multiresolution signal processing, our mesh watermarking algorithm can be integrated naturally with the multiresolution mesh processing toolbox. To detect watermarks, registration and resampling are needed to bring the attacked mesh model back into its original location, orientation, scale, topology and resolution level. Experimental results and attack analysis are given to show that our watermarking algorithm is robust under a variety of attacks, including vertex reordering, noise addition, simplification, filtering and enhancement, cropping, etc. Our main contribution to the field of 3D watermarking is that we propose a generic applicable multiresolution framework in which other proposed techniques may fit in as well.

This paper is devoted to a designer tool, which is an extension of particle tracing algorithm for analysis of scenes, artifacts, image ghosts, and ray-tracing mechanism itself. The global illumination problem here is considered at the level of light propagation visualization, which takes into account all cognitive benefits of visual representation. Physically accurate particle tracers randomly generate thousands of rays per second to simulate light propagation in a scene considering light as consisting of photons with a constant energy. The proposed tool utilizes and filters the information of how light photons propagate in the scene. Several examples in the paper demonstrate a practical value of obtained photon tracks for scene analysis.

This paper describes an interactive aircraft surface engineering and grid generation system Zeus, that has been developed and one that has evolved with actual use over the last decade. Zeus is an interactive system for the design, specification and visualization of aircraft geometries. The package supports surfaces defined in a number of representations including planes, spheres, cylinders, bilinear surfaces, NURBS and triangulated surfaces. It includes fairly sophisticated geometric editing and rendering operations. It derives its main strength from the fact that it includes a comprehensive suite of tools for surface and volume grid generation and their visualization. During these ten years of development, there have been a number of innovative computational techniques and algorithms that have been devised, implemented and tested. This paper is primarily about the Zeus system and these new innovative techniques.

This paper addresses the important issue of automating grasping movement in the animation of virtual actors, and presents a methodology and algorithm to generate realistic looking grasping motion of arbitrary shaped objects. A hybrid approach using both forward and inverse kinematics is proposed. A database of predefined body postures and hand trajectories are generalized to adapt to a specific grasp. The reachable space is divided into small subvolumes, which enables the construction of the database. The paper also addresses some common problems of articulated figure animation. A new approach for body positioning with kinematic constraints on both hands is described. An efficient and accurate manipulation of joint constraints is also presented. Finally, we describe an interpolation algorithm which interpolates between two postures of an articulated figure by moving the end effector along a specific trajectory and maintaining all the joint angles in the feasible range. Results are quite satisfactory, and some are shown in the paper.

Reconstructing the surfaces of objects from planar contours can be done by either tiling (connecting contours with polygonal facets) or skinning (connecting contours with parametric spline surfaces). In this paper, we break down the surface reconstruction problem into three steps for tiling (grouping, transition, tiling) and four steps for skinning (grouping, transition, parameter correspondence, skinning). Many techniques for completing the grouping, tiling and skinning steps exist. However, the transition step, while treated in the literature, does not have an adequate solution for the most general contours. In this paper, we present a computational technique for completing the transition step, as well as offer new solutions to the grouping and parameter correspondence steps. Our techniques are implemented in a computer environment for a variety of multi-branched objects whose contours vary significantly in shape. In addition it requires no user interaction. Illustrative examples are included.

In this paper we propose new methods for calculating the projection of an opaque 3-dimensional 6-connected volumetric object into a two-dimensional view using 2- and 2 1 2 -dimensional seed-filling in the view space. When a 3-dimensional volumetric data set is sampled by parallel rays at a resolution exceeding the Nyquist ratio, the 6-connectivity of objects is maintained from volume lattice to view lattice. Given a seed point for each 6-connected object in the volumetric data set, a seed-filling algorithm may access all sample points in view lattice, while simultaneously composing the rendered view. The algorithms presented in this paper minimize the number of voxels that need to be processed. We implemented these methods on a general purpose computer architecture and tested them with several artificial and real-life medical volumetric data sets. It is shown that the algorithms may be used to speed up the parallel ray casting of opaque medical objects. The actual frame rate achieved by the combined method allows interactive (10 frames/sec) rotation of the object on a common single-processor personal computer without specialized hardware.

International audience; In highly dense crowds of humans, collisions between people occur often. It is common to simulate such a crowd as one fluid-like entity (macroscopic), and not as a set of individuals (microscopic, agent-based). Agent-based simulations are preferred for lower densities because they preserve the properties of individual people. However, their collision handling is too simplistic for extreme-density crowds. Therefore, neither paradigm is ideal for all possible densities. In this paper, we combine agent-based crowd simulation with Smoothed Particle Hydrodynamics (SPH), a particle-based method that is popular for fluid simulation. We integrate SPH into the crowd simulation loop by treating each agent as a fluid particle. The forces of SPH (for pressure and viscosity) then augment the usual navigation behavior and contact forces per agent. We extend the standard SPH model with a dynamic rest density per particle, which intuitively controls the crowd density that an agent is willing to accept. We also present a simple way to let agents blend between individual navigation and fluid-like interactions depending on the SPH density. Experiments show that SPH improves agent-based simulation in several ways: better stability at high densities, more intuitive control over the crowd density, and easier replication of wave-propagation effects. Also, density-based blending between collision avoidance and SPH improves the simulation of mixed-density scenarios. Our implementation can simulate tens of thousands of agents in real-time. As such, this work successfully prepares the agent-based paradigm for crowd simulation at all densities.