Search

Maximally stable component detection is a very popular method for feature analysis in images, mainly due to its low computation cost and high repeatability. With the recent advance of feature-based methods in geometric shape analysis, there is significant interest in finding analogous approaches in the 3D world. In this paper, we formulate a diffusion-geometric framework for stable component detection in non-rigid 3D shapes, which can be used for geometric feature detection and description. A quantitative evaluation of our method on the SHREC'10 feature detection benchmark shows its potential as a source of high-quality features.

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.

We present an approach to compute the perceived complexity of a given 3D shape using the similarity between its views. Previous studies on 3D shape complexity relied on geometric and/or topological properties of the shape and are not appropriate for incorporating results from human shape perception which claim that humans perceive 3D shapes as organizations of 2D views. Therefore, we base our approach to computing 3D shape complexity on the (dis)similarity matrix of the shape's 2D views. To illustrate the application of our approach, we note that simple shapes lead to similar views whereas complex ones result in different, dissimilar views. This reflected in the View Similarity Graph (VSG) of a shape as tight clusters of points if the shape is simple and increasingly dispersed points as it gets more complex. To get a visual intuition of the VSG, we project it to 2D using Multi-Dimensional Scaling (MDS) and introduce measures to compute shape complexity through point dispersion in the resulting MDS plot. Experiments show that results obtained using our measures alleviate some of the drawbacks present in previous approaches.

A common variant of caricature relies on exaggerating characteristics of a shape that differs from a reference template, usually the distinctive traits of a human portrait. This work introduces a caricature tool that interactively emphasizes the differences between two three-dimensional meshes. They are represented in the manifold harmonic basis of the shape to be caricatured, providing intrinsic controls on the deformation and its scales. It further provides a smooth localization scheme for the deformation. This lets the user edit the caricature part by part, combining different settings and models of exaggeration, all expressed in terms of harmonic filter. This formulation also allows for interactivity, rendering the resulting 3d shape in real time.

In recent years, with the improvement of artificial intelligence technology, it has become possible to reconstruct high-precision 3D human body models based on ordinary RGB images. The current 3D human body reconstruction technology requires complex external equipment to scan all angles of the human body, which is complicated to be implemented and cannot be popularized. In order to solve this problem, this paper applies deep learning models on reconstructing 3D human body based on monocular images. First of all, this paper uses Stacked Hourglass network to perform convolution operations on monocular images collected from different views. Then Multi-Layer Perceptrons (MLPs) are used to decode the encoded high-level images. The feature codes in the two views(main and side) are fused, and the interior and exterior points are classified by the fusion features, so as to obtain the corresponding 3D occupancy field. At last, the Marching Cube algorithm is used for 3D reconstruction with a specific threshold and then we use Laplace smoothing algorithm to remove artifacts. This paper proposes a dense sampling strategy based on the important joint points of the human body, which has a certain optimization effect on the realization of high-precision 3D reconstruction. The performance of the proposed scheme has been validated on the open source datasets, MGN dataset and the THuman dataset, provided by Tsinghua University. The proposed scheme can reconstruct features such as clothing folds, color textures, and facial details,and has great potential to be applied in different applications.

The primary purpose of this paper is to realize robust place recognition algorithms towards simultaneous viewpoint and condition changes, and provide satisfactory computational efficiency. In this paper, we significantly improve the viewpoint invariance of the SeqSLAM algorithm by using state-of-the-art deep learning techniques to generate robust feature representations of images and develop the SeqCNNSLAM. Experimental results show that SeqCNNSLAM outperforms state-of-the-art place recognition systems in most cases, such as, when precision is maintained at 100%, the maximum recall obtained by SeqCNNSLAM is 50% higher than SeqSLAM on the Norland dataset with simultaneous condition change and 12.5% viewpoint change. Besides, we develop an acceleration method called A-SeqCNNSLAM, which exploits the location relationship between the matching images of adjacent images to reduce the matching range of the current image. Experimental results demonstrate that an acceleration of ∼ 5 times is achieved with minimal accuracy degradation of ∼ 5%. Finally, to enable A-SeqCNNSLAM adaptability in new environments, O-SeqCNNSLAM is devised for the online parameter adjustment in A-SeqCNNSLAM.

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

Flexible visual analysis of long, high-resolution, and irregularly sampled time series data from multiple sensor streams is a challenge in several domains. In the field of additive manufacturing, this capability is critical for realizing the full potential of large-scale 3D printers. In this paper, we propose a visual analytics approach that helps additive manufacturing researchers acquire a deep understanding of patterns in log and imagery data collected by 3D printers. Specific goals include discovering patterns related to defects and system performance issues, optimizing build configurations to avoid defects, and increasing production efficiency. We introduce Falcon, a new visual analytics system that allows users to interactively explore large, time-oriented data sets from multiple linked perspectives. Falcon provides overviews, detailed views, and unique segmented time series visualizations, all with adjustable scale options. To illustrate the effectiveness of Falcon at providing thorough and efficient knowledge discovery, we present a practical case study involving experts in additive manufacturing and data from a large-scale 3D printer. Although the focus of this paper is on additive manufacturing, the techniques described are applicable to the analysis of any quantitative time series.

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.

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.

Computer generated images are most easily generated as pinhole images whereas images obtained with optical lenses exhibit a Depth-of-Field (DOF) effect. This is due to the fact that optical lenses gather light across finite apertures whereas the simulation of a pinhole lens means that the light is gathered through an infinitesimal small aperture, thus producing sharp images at any depth. Simulating the physical process of gathering light across a finite aperture can be done for example with distributed ray tracing, but it is computationally much more expensive than the simulation through an infinitesimal aperture. The usual way of simulating lens effects is therefore to produce a pinhole image and then post processes the image to approximate the DOF. Post processing algorithms are fast but suffer from incorrect visibilities. In this paper, we propose a novel algorithm that tackles the visibility issue with a sparse set of views rendered through the optical center of the lens and several peripheral viewpoints distributed on the lens. All peripheral images are warped towards the central view to create a Layered-Depth-Image (LDI), so that all observed 3D points located on the same central view-ray are stacked on the same pixel of the LDI. Then, each pixel in the LDI is conceptually scattered into a Point-Spread-Function (PSF) and blended in depth order. While the scatter method is very inefficient on a GPU, we propose a selective-gather method for DOF synthesis, which scans the neighborhood of a pixel and blends the colors from the PSFs covering the pixel. Experiments show that the proposed algorithm can synthesize high-quality DOF effects close to the results of distributed ray tracing but at a much higher speed. Display Omitted HighlightsThe paper discusses a fast algorithm for DOF simulation from a sparse set of pinhole images.The algorithm provides simulations of DOF effects close to those produced by distributed ray tracing but at a significantly lower cost.

Focus plus context visualization can be used in augmented reality to improve the visual perception of the augmented scene. In the scope of in situ or on-patient medical data visualization, the focus plus context paradigm is used to improve depth perception for physicians showing the patient's anatomy as a focus region in the context of the patient's body. Volume clipping is one technique to realize focus plus context visualization. However, some of the existing methods for focus plus context visualization based on volume clipping do not run in full real time or are prone to artifacts. In this paper, we present an extension for two of these techniques to improve performance and image quality of the original approaches. We validate all the techniques in a markerless augmented reality environment. A 3D reference model is tracked by the application, and volumetric medical data are shown to the user at the position of the patient's anatomy. Our technique is able to handle multiple anatomic regions, although the main region of interest used in this paper is the face. Moreover, tracking accuracy is improved by the use of a hierarchical approach. From an evaluation of the proposed techniques, the results obtained highlight that all of them are free of artifacts, optimized for real-time performance, and improve the visual quality of the augmented scene. Graphical abstractDisplay Omitted HighlightsImprovement of smooth contours technique to achieve real-time performance.Improvement of visible background on MRI data to achieve higher visual quality.Use of a hierarchical ICP algorithm to improve tracking accuracy.Extension of the on-patient visualization for different parts of the patient's body.

Smart products, adaptive designs, and intelligent spaces are in the forefront of current artistic discourse. Regardless of oneÂ?s field - design or science - interaction design projects often benefit from efficient production methods for prototypes for beginners. This paper presents an educational case study and its pedagogical lessons from a project-based course for beginning design students to produce interactive prototypes using sensors, actuators, and microcontrollers. A series of short project-based modules using scaffolding of code templates in conjunction with toolkits for physical prototypes were introduced in order to learn fundamental technical knowledge and skills in the first half; then more open-ended investigation of project-based individual creative final projects followed. Each module can be completed in one day with instructions on prototyping and programming in pairs, allowing students to build and see abstract logic in programming through the physical behaviors of prototypes without overpowering student creativity and motivation. Students can reinterpret given materials and modify them to produce custom tools that can realize their original project goals. This strategy allows students to acquire extensible knowledge that does not rely on higher-level software functions or specialized but inflexible plug-ins. This paper is an extended and revised version of a paper presented at the EUROGRAPHICS 2014 conference 30]. Graphical abstractDisplay Omitted HighlightsThe paper introduces interactive prototypes produced by design students.The project-based approach with practical learning modules yields creative results.Learning modules consist of digital fabrication and programming techniques in pairs.The proposed teaching approach can be applied to fields other than design.The approach provides students experience in interdisciplinary collaboration.

In order to improve registration performance of mobile augmented reality initialization, a new CAD-based recognition method of 3D objects in monocular images is proposed in this paper. Instead of estimating camera pose directly, our method attempts to estimate 3D object pose in the camera coordinate system. The geometric correspondence between the object mass center and its projection on 2D camera image is used to estimate object position. To hypothesize possible azimuths of the object, the 3D CAD model is off-screen rendered with OpenGL ES at different azimuths under an assumed inclination constraint provided by the inertial sensors of mobile devices, and compared with input image by contours matching. Unlike most recognition methods based on machine learning and natural features detection, which require large databases of real images and heavy computational consumption, our method only needs the CAD model of the 3D object in offline stage, and is computationally suitable for mobile devices. This paper describes the details of the method and shows its effectiveness with experiments. Graphical abstractDisplay Omitted HighlightsWe analyze limitations of conventional recognition methods for mobile devices.Geometric features and internal sensors are used to reduce the search space.We determine objects azimuths by CAD models rendering and contours matching.All we need is only the object?s CAD model without any other offline work.Our solution provides a novel perspective on recognition.

Despite the benefits of presence, immersive virtual reality is still too limiting and ineffective to be widely adopted in people?s everyday lives. One important reason for this is its inability to handle highly diverse 3D interaction tasks, such as object manipulation from different scales, perspectives, reference frames, and dimensions. Inspired by preliminary development of an immersive world builder tool, this paper offers an in-depth presentation of our solution to this problem, using a coordinated, tablet- and HMD-based, hybrid virtual environment (HVE) system. Wearing a non-occlusive HMD, the user is able to view and interact with a tablet mounted on the non-dominant forearm, which provides a multi-touch interaction surface, as well as an exocentric God view of the virtual world. To reduce transition gaps across 3D interaction tasks and interfaces, four coordination mechanisms are proposed, two of which were implemented, and one was evaluated in a user study featuring complex level-editing tasks. Based on subjective ratings, task performance, interview feedback, and video analysis, we found that having multiple seamless Interaction Contexts (ICs) with complementary benefits can lead to good performance and user experience, despite the complexity of learning and using the hybrid system. The results also suggest keeping 3DUI tasks synchronized across the ICs, as this can help users understand their relationships, smoothen within- and between-task IC transitions, and inspire more creative use of different interfaces. Finally, based on these findings, a four-step design process is proposed to aid the process of designing and implementing HVE systems, as well as applying them to appropriate task scenarios. Graphical abstractThis paper proposes using a tablet- and HMD-based, coordinated hybrid virtual environment system to enable effective 3D interaction in immersive virtual reality.Display Omitted HighlightsWe built a novel hybrid virtual environment system for effective interaction in VR.We propose four coordination mechanisms to smoothen context transitions in HVEs.We conducted a user study and proved task synchronization can reduce transition gap.The study shows a complex HVE system can be mastered to benefit interaction in VR.We propose a four-step guideline to aid the design, develop, and application of HVEs.

The visualization of simulation trajectories is a well-established approach to analyze simulated processes. Likewise, the visualization of the parameter space that configures a simulation is a well-known method to get an overview of possible parameter combinations. This paper follows the premise that both of these approaches are actually two sides of the same coin; since the input parameters influence the simulation outcome, it is desirable to visualize and explore both in a combined manner. The main challenge posed by such an integrated visualization is the combinatorial explosion of possible parameter combinations. It leads to insurmountably high simulation runtimes and screen space requirements for their visualization. The Visual Analytics approach presented in this paper targets this issue by providing a visualization of a coarsely sampled subspace of the parameter space and its corresponding simulation outcome. In this visual representation, the analyst can identify regions for further drill-down and thus finer subsampling. We aid this identification by providing visual cues based on heterogeneity metrics. These indicate in which regions of the parameter space deviating behavior occurs at a more fine-grained scale and thus warrants further investigation and possible re-computation. We demonstrate our approach in the domain of systems biology by a visual analysis of a rule-based model of the canonical Wnt signaling pathway that plays a major role in embryonic development. In this case, the aim of the domain experts was to systematically explore the parameter space to determine those parameter configurations that match experimental data sufficiently well.

Sketch-based modeling has attracted considerable attention in recent years. In this paper, we propose a semantic feature modeling system for sketch-based jewelry design, called blue Sketch2Jewelry. The newly devised semantic feature class encodes specific domain knowledge (jewelry design knowledge in this paper) and supplies prolific semantic information. The advantage of using semantic features is to narrow down the searching space in sketch-based feature retrieval and benefits the parameter selection from input sketches for feature instantiation and feature placement. Thus, the inaccuracy and ambiguity problems of freehand sketch inputs are alleviated within Sketch2Jewelry, compared to previous commercial feature-based modeling tools, e.g. SolidWorks, which are limited to fake sketches (i.e. not real freehand inputs). Since semantic features are high-level building blocks, together with sketch inputs, the proposed Sketch2Jewelry system can significantly improve the jewelry design efficiency. In addition, Sketch2Jewelry allows non-experts to sketch a complex jewelry model naturally and efficiently with design-by-feature. Examples are provided to demonstrate its usefulness.

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.

Afterimages comprise a common, recurring perceptual phenomenon experienced on a daily basis. Afterimages are best realized when staring at some high-intensity light source (i.e., a light bulb) and then changing the fixation to other less luminous portions of the scene: a temporary ''ghost'' image of that strong intensity remains noticeable for a period of time. During the time the afterimage stays active, several color gradations appear and fade, with little resemblance to the color that originally stimulated them. Although research on the topic has been moderately active in the ophthalmology and vision domains, no definitive model has been devised. In computer graphics, research on afterimages remains young. In this paper we propose a technique that addresses the duration as well as the luminance and color transitions of the effect, all inspired by psychophysical and physiological evidence. The main contribution of this paper is a model for color transitions in afterimages (also known as flight-of-colors). To our knowledge, no record exist on the subject in the computer graphics literature. The proposed method is also fast and suitable for real-time applications. Our stance towards afterimages is more than just curiosity on this peculiar effect and we believe that its understanding and proper simulation can assist on relevant tasks such as urban and road engineering for safer pedestrian and vehicle mobility at adverse lighting conditions.

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.

International audience; Cosine functions have been widely used for representing Bidirectional Reflection Distribution Functions (BRDF) such as Lambert, Phong and Lafortune models. They are well suited to represent both high and low frequency signals. However, they are difficult to use with visibility and incident radiance. In most systems, the rendering equation terms are thus estimated using various methods. Several interactive rendering systems rather rely on the projection of each term onto orthonormal basis functions such as spherical harmonics or wavelets. These methods are easier to handle since the integration becomes a dot product. However, these functions are also subject to several drawbacks. For instance the number of coefficients is high for the representation of high frequency phenomena; the precomputation time required for projecting each term of the rendering equation cannot be neglected. This paper demonstrates that cosine lobes can be generalized to visibility and incoming radiance with several advantages. First, cosine lobes do not form an orthonormal basis of functions and the number of parameters remains naturally adapted to the signal. This is very interesting for complex and high frequency functions: glossy BRDF or small light sources for instance. We also use this property for reducing the number of parameters as the computation goes along. Second, Lambert, Phong and Lafortune BRDF models are already used in many rendering systems. Since they already rely on this representation, no transformation into other types of model is necessary. This paper shows how it is possible to rapidly integrate the product of cosine lobes. As a demonstration of our methodology, we propose an interactive rendering system for direct lighting, including soft shadows and spatially varying materials.

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.

In this paper we shall review the major approaches done in the past concerning the development of immersive artistic installations. This will permit one to identify the basic features to be attained by this kind of installations and based on them a new cooperative and autonomous robotic platform will be proposed. The major novelty of the approach presented in this paper relies on its short- and long-term adaptation capabilities. The technical details of its basic building blocks and the results of the preliminary field tests will be provided, showing that it constitutes a very efficient platform for the construction of actual adaptive and immersive artistic installations.

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.

There is a growing demand for design support to create interactive systems that are deployed in ambient intelligent environments. Unlike traditional interactive systems, the wide diversity of situations these type of user interfaces need to work in require tool support that is close to the environment of the end-user on the one hand and provide a smooth integration with the application logic on the other hand. This paper shows how the model-based user interface development methodology can be applied for ambient intelligent environments; we propose a task-centered approach towards the design of interactive systems by means of appropriate visualizations and simulations of different models. Besides the use of these typical user interface models such as the task- and presentation-model to support interface design, we focus on user interfaces supporting situated task distributions and a visualization of context influences on deployed, possibly distributed, user interfaces. To enable this we introduce an environment model describing the device configuration at particular moment in time. To support the user interface designer while creating these complex interfaces for ambient intelligent environments, we discuss tool support using a visualization of the environment together with simulations of the user interface configurations. We also show how the concepts presented in the paper can be integrated within model-driven engineering, hereby narrowing the gap between HCI design and software engineering.

In this paper, we present some of the problems we have faced in visualizing patterns coming from Chua's circuit, with the main aim of sharing these investigations with researchers in Computer Graphics. Furthermore, the paper deals about advanced Computers Graphics techniques for managing complexity in representing chaotic and hyperchaotic systems. The problems we have faced deal about the nature of these configurations, their shapes and dimensions, the granularity of these objects, since the output could be made of different elements such as cubes, cylinders and so on. Instead, cognitive issues related to perception of forms in 3D spaces and their recognition are still unexplored.

Deep learning (DL) models have achieved impressive performance in various domains such as medicine, finance, and autonomous vehicle systems with advances in computing power and technologies. However, due to the black-box structure of DL models, the decisions of these learning models often need to be explained to end-users. Explainable Artificial Intelligence (XAI) provides explanations of black-box models to reveal the behavior and underlying decision-making mechanisms of the models through tools, techniques, and algorithms. Visualization techniques help to present model and prediction explanations in a more understandable, explainable, and interpretable way. This survey paper aims to review current trends and challenges of visual analytics in interpreting DL models by adopting XAI methods and present future research directions in this area. We reviewed literature based on two different aspects, model usage and visual approaches. We addressed several research questions based on our findings and then discussed missing points, research gaps, and potential future research directions. This survey provides guidelines to develop a better interpretation of neural networks through XAI methods in the field of visual analytics.

Refereed/Peer-reviewed This paper presents an Augmented Reality (AR)-based network cabling tutoring system that trains users how to interconnect cables within a Virtual Local Area Network (VLAN) on a physical switching rack. AR arrows combined with text-based instruction and a checklist provided assistance during practical learning. When learners made a mistake, an Intelligent Tutoring System (ITS) identified the source of the mistake and provided real-time feedback using text, AR and text-to-speech mechanisms. The design was motivated by the human-cognitive architecture and its five evolutionary principles (proposed by Sweller and Sweller (2006)). Users performed four consecutive network cabling training tasks with assistance from our ITS. We found that users made fewer errors when the AR cues, text-based instruction and checklist solutions were replaced with summarised information and then removed completely in the final task compared to those who used an identical system with fixed instruction. Cognitive Load Theory (CLT) explains our results by suggesting that the instructional mechanisms become redundant as knowledge increases. Implications of the study are discussed as well as how AR can help facilitate knowledge transfer in the network cabling domain.

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

The representation of consistent mixed reality (XR) environments requires adequate real and virtual illumination composition in real-time. Estimating the lighting of a real scenario is still a challenge. Due to the ill-posed nature of the problem, classical inverse-rendering techniques tackle the problem for simple lighting setups. However, those assumptions do not satisfy the current state-of-art in computer graphics and XR applications. While many recent works solve the problem using machine learning techniques to estimate the environment light and scene’s materials, most of them are limited to geometry or previous knowledge. This paper presents a CNN-based model to estimate complex lighting for mixed reality environments with no previous information about the scene. We model the environment illumination using a set of spherical harmonics (SH) environment lighting, capable of efficiently represent area lighting. We propose a new CNN architecture that inputs an RGB image and recognizes, in real-time, the environment lighting. Unlike previous CNN-based lighting estimation methods, we propose using a highly optimized deep neural network architecture, with a reduced number of parameters, that can learn high complex lighting scenarios from real-world high-dynamic-range (HDR) environment images. We show in the experiments that the CNN architecture can predict the environment lighting with an average mean squared error (MSE) of 7.85 × 10−4 when comparing SH lighting coefficients. We validate our model in a variety of mixed reality scenarios. Furthermore, we present qualitative results comparing relights of real-world scenes.

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.

Nowadays, computer graphics courses are usually taught with traditional teaching methodologies and tools, which have several limitations. In this paper, we present an online interactive computer graphics (CG) tutorial, which supports the collaborative learning of the concepts and algorithms of computer graphics in a networked virtual environment. The practical part of the tutorial consists of example programs for users to test the theoretical concepts and to obtain their own experiments. The integration of the different theoretical and practical parts of the course is realized through a common Web-based interface to the system. The main objectives are to (1) allow the users to learn and practice with the algorithms of computer graphics in a virtual environment, (2) support avatar-based collaborative learning based on avatars involving, several users connected through the Internet. Two versions of the system in Chinese and English language, respectively, have been implemented and are described in the paper.

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.

In this paper the new method of understanding of the curve-polygon object is presented. The method of understanding of the curve-polygon object is part of the research aimed at developing a shape understanding method able to perform complex visual tasks connected with visual thinking. The shape understanding method is implemented as the shape understanding system (SUS). Understanding includes, among others, obtaining the visual concept in process of the visual reasoning, naming and visual explanation by generation an object from a required class. In this paper generation of the object from the selected well defined class, the curve-polygon class, as well as assigning the visual object into one of the shape classes is presented. The generation of the visual objects is used in SUS during learning of the visual concept, explanatory process and self-correcting process. The visual object is assigned into one of the shape classes during the visual reasoning process. The visual reasoning, presented in this paper, in contrast to other forms of reasoning depends on the type of objects which are analysed. In this paper visual reasoning that assigns an object to the curve-polygon class is presented. The shape understanding system consists of different types of experts that perform different processing and reasoning tasks. The self-correcting expert, that implements the new method of testing and reasoning, is invoked to test ability of the system to understand the concept of the curve-polygon shape.

This paper depicts the Portuguese interactive television (iTV) market focusing on the novel applications produced in that market between the years 2001 and 2003. Particular focus is given to two applications, “Noites Interactivas” and “VEMiTV-PANDA”, not only from a technological point of view, but also from the user interaction point of view. These two examples are used to illustrate the challenges facing iTV services technological deployment and commercial development. The paper ends by summarising the lessons taken from the service deployment in Portugal and showing who is ahead in the everlasting balance between technology and content.

A novel method of noise reduction in color images is presented in this paper. This new technique is capable of attenuating impulsive and Gaussian noise, while preserving and even enhancing sharpness of the image edges. In the paper a smoothing operator, based on a random walk model and a fuzzy similarity measure between pixels connected by digital geodesic paths, is introduced. Extensive simulations reveal that the new method outperforms the standard techniques commonly used in multivariate signal processing.

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 new approach to classify, index and retrieve technical drawings by content. Our work uses spatial relationships, visual elements and high-dimensional indexing mechanisms to retrieve complex drawings from CAD databases. This contrasts with conventional approaches which use mostly textual metadata for the same purpose. Creative designers and draftspeople often reuse data from previous projects, publications and libraries of ready to use components. Usually, retrieving these drawings is a slow, complex and error-prone endeavor, requiring either exhaustive visual examination, a solid memory, or both. Unfortunately, the widespread use of CAD systems, while making it easier to create and edit drawings, exacerbates this problem, insofar as the number of projects and drawings grows enormously, without providing adequate retrieval mechanisms to support retrieving these documents. In this paper, we describe an approach that supports automatic indexing of technical drawing databases through drawing simplification techniques based on geometric features and efficient algorithms to index large amounts of data. We describe in detail the indexing structure (NB-Tree) we have developed within the context of a more general approach. Experimental evaluation reveals that our approach outperforms some of the best indexing structures published, enabling us to search very large drawing databases.

Virtual prototyping tools have already captivated the industry's interest as viable design tool. One of the key challenges for the research community is to extend the capabilities of Virtual Reality technology beyond its current scope of ergonomics and design reviews. The research presented in this paper is part of a larger research programme that aims to perform maintainability assessment on virtual prototypes. This paper discusses the design and implementation of a geometric constraint manager that has been designed to support physical realism and interactive assembly and disassembly tasks within virtual environments. The key techniques employed by the constraint manager are direct interaction, automatic constraint recognition, constraint satisfaction and constrained motion. Various optimization techniques have been implemented to achieve real-time interaction with large industrial models.

This paper presents the method of understanding objects that can be considered as thin objects. The proposed method of understanding thin objects is part of the shape understanding method developed by the author. The main novelty of the presented method is that the process of understanding thin objects is related to the visual concept represented as a symbolic name of the possible class of shapes. The possible classes of shape, viewed as hierarchical structures, are incorporated into the shape model. At each stage of the reasoning process that led to assigning of an examined object to one of the possible classes, novel processing methods are used. These methods are very efficient because they deal with a very specific class of shapes. In this paper, the 2-D objects that are classified as thin objects are regarded as geometrical objects without any reference to the real world objects. However, the shape under standing method is designed to understand an object at many levels of interpretation, such as the topological level, the linguistic level and the real world reference level. This approach influences the way in which the system of shape understanding is designed. The system consists of different types of experts that perform different processing and reasoning tasks.

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 .

The objective of this paper is to explain the machinery of the Chaos Game used in the context of various types of iterated function system specifications. Although the discussion is kept in the framework of a mathematical proof, in contrast to the previous work, only the fundamentals of probability are employed. Moreover, unlike the known approaches, the way of reasoning presented in this paper is the same for all the discussed variants of the Chaos Game. As a result, the logical background of the algorithm can be followed by anyone who is interested in fractals and computer graphics.

Volume rendering, the projection of volumetric intensity data into a 2D image, is finding an increasing number of applications across a diverse range of scientific disciplines. A key ingredient in the volume rendering recipe is a procedure to allow the user to specify a limited volume of interest, since rendering the entire volume is often too slow and also leaves the image full of clutter that obscures genuine structures of interest: this is particularly important for 3D ultrasound, where speckle noise has traditionally frustrated the successful application of volume rendering. This paper describes novel techniques, tuned to the specific needs of 3D ultrasound, for specifying these target volumes. The basic idea is to extend the familiar planar and non-planar reslicing tools, such that the reslice plane or surface is endowed with a certain thickness, producing a narrow-band volume. The attraction of such volumes is that they are simple to set up, limit the amount of clutter in the final renderings and, when thin, produce reslice-like images that are far less sensitive to the precise position of the reslice plane (or surface) than those generated by standard reslice algorithms. The paper includes full implementation details of both planar and non-planar narrow-band volume rendering, and describes several practical applications of the resulting tools.

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.

With the expanded digitalization of manufacturing and product development process, research into the use of immersive technology in smart manufacturing has increased. The use of immersive technology is theorized to increase the productivity of all steps in the product development process, from the start of the concept generation phase to assembling the final product. Many aspects of immersive technology are considered, including techniques for CAD model conversion and rendering, types of VR/AR displays, interaction modalities, as well as its integration with different areas of product development. The purpose of this survey paper is to investigate the potential applications of immersive technology and advantages and potential drawbacks that should be considered when integrating the technology into the workplace. The potential application is broad, and the possibilities are continuing to expand as the technology used becomes more advanced and more affordable for commercial business to implement on a large scale. The technology is currently being utilized in the concept generation and in the design or engineering of new products. Additionally, the immersive technology have great potential to increase the productivity of assembly line workers and of the factory layout/functionality, and could provide a more hands-on form of training, which leads to the conclusion that immersive technology is the step to the future in terms of smart product development strategies to implement for employers.

We developed a virtual road crossing assessment tool called iVRoad - immersive Virtual Road, which allows to put the patient into realistic road crossing situations and to record various parameters that can be used to quantify unilateral spatial neglect. We present a study with 18 stroke patients in which we evaluate our system with respect to usability, satisfaction, sense of presence and possible occurring cybersickness symptoms. Unilateral spatial neglect is a cognitive disturbance, often occurring after right hemispheric stroke. Conventional neuropsychological tests, such as paper-and-pencil tests, for assessing unilateral spatial neglect, often lack sensitivity. Especially in mild forms, symptoms can be seen in everyday life, but are hard to detect in formal testing. We examined patients with and without unilateral spatial neglect in order to identify parameters that could be feasible to separate these patient groups. Using everyday life tasks as a diagnostic instrument, however, is challenging because it is time-consuming, hard to control and to quantify. Computer-aided diagnostic systems are promising for analysing the behaviour of patients in detail. Modern virtual reality technology allows to place the patient in realistic situations. Especially situations in which patients often have difficulties or that are too dangerous in reality can be assessed with VR.