Search

Hand-object interaction is challenging to reconstruct but important for many applications like HCI, robotics and so on. Previous works focus on either the hand or the object while we jointly track the hand poses, fuse the 3D object model and reconstruct its rigid and nonrigid motions, and perform all these tasks in real time. To achieve this, we first use a DNN to segment the hand and object in the two input depth streams and predict the current hand pose based on the previous poses by a pre-trained LSTM network. With this information, a unified optimization framework is proposed to jointly track the hand poses and object motions. The optimization integrates the segmented depth maps, the predicted motion, a spatial-temporal varying rigidity regularizer and a real-time contact constraint. A nonrigid fusion technique is further involved to reconstruct the object model. Experiments demonstrate that our method can solve the ambiguity caused by heavy occlusions between hand and object, and generate accurate results for various objects and interacting motions. [ABSTRACT FROM AUTHOR]

We propose a novel 360° scene representation for converting real scenes into stereoscopic 3D virtual reality content with head-motion parallax. Our image-based scene representation enables efficient synthesis of novel views with six degrees-of-freedom (6-DoF) by fusing motion fields at two scales: (1) disparity motion fields carry implicit depth information and are robustly estimated from multiple laterally displaced auxiliary viewpoints, and (2) pairwise motion fields enable real-time flow-based blending, which improves the visual fidelity of results by minimizing ghosting and view transition artifacts. Based on our scene representation, we present an end-to-end system that captures real scenes with a robotic camera arm, processes the recorded data, and finally renders the scene in a head-mounted display in real time (more than 40 Hz). Our approach is the first to support head-motion parallax when viewing real 360° scenes. We demonstrate compelling results that illustrate the enhanced visual experience — and hence sense of immersion-achieved with our approach compared to widely-used stereoscopic panoramas. [ABSTRACT FROM PUBLISHER]

Blue noise sampling is an important component in many graphics applications, but existing techniques consider mainly the spatial positions of samples, making them less effective when handling problems with non-spatial features. Examples include biological distribution in which plant spacing is influenced by non-positional factors such as tree type and size, photon mapping in which photon flux and direction are not a direct function of the attached surface, and point cloud sampling in which the underlying surface is unknown a priori. These scenarios can benefit from blue noise sample distributions, but cannot be adequately handled by prior art. Inspired by bilateral filtering, we propose a bilateral blue noise sampling strategy. Our key idea is a general formulation to modulate the traditional sample distance measures, which are determined by sample position in spatial domain, with a similarity measure that considers arbitrary per sample attributes. This modulation leads to the notion of bilateral blue noise whose properties are influenced by not only the uniformity of the sample positions but also the similarity of the sample attributes. We describe how to incorporate our modulation into various sample analysis and synthesis methods, and demonstrate applications in object distribution, photon density estimation, and point cloud sub-sampling. [ABSTRACT FROM AUTHOR]

In most realtime applications such as 3D games, in order to reduce the complexity of the scene being rendered, objects are often made by simple and large primitives. Thus, the phenomenon of edge highlighting, which would require chamfering structures made by lots of small patches at the seaming, is absent and is often faked by 'highlights' drawn on the texture. We proposed a realistic realtime rendering procedure for highlighting chamfering structures, or rounded edges, by considering specified edges as thin cylinders and obtained the intensity via integration. We derived a brief approximated formula generalized from Blinn's shadow model, and used a precomputed integration table to accelerate the render speed and reduce resources needed. The algorithm is implemented with shader language, and can be considered as a post-process on original result. Evaluation shows that the effect on rendering speed is limited even for scenes with large scale of vertices. [ABSTRACT FROM AUTHOR]

We propose a specialized form of the curved-knot B-spline surface of Hayes [1982] that we call regular curved-knot spline surface. Unlike the original formulation where the knots of the first parametric coordinate can evolve arbitrarily with respect to the second coordinate, our formulation designs the knot functions as special curves that guarantee a monotonic blending of the knots corresponding to opposite surface boundaries. Furthermore, we demonstrate that local derivatives on the boundary can be described as an ordinary B-spline surface. The latter property allows for constructing smooth transitions between B-spline boundaries with different knot vectors. [ABSTRACT FROM AUTHOR]

We present a novel artistic-verisimilitude driven system for watercolor rendering of images and photos. Our system achieves realistic simulation of a set of important characteristics of watercolor paintings that have not been well implemented before. Specifically, we designed several image filters to achieve: 1) watercolor-specified color transferring; 2) saliency-based level-of-detail drawing; 3) hand tremor effect due to human neural noise; and 4) an artistically controlled wet-in-wet effect in the border regions of different wet pigments. A user study indicates that our method can produce watercolor results of artistic verisimilitude better than previous filter-based or physical-based methods. Furthermore, our algorithm is efficient and can easily be parallelized, making it suitable for interactive image watercolorization. [ABSTRACT FROM PUBLISHER]

We propose a specialized form of the curved-knot B-spline surface of Hayes [1982] that we call regular curved- knot spline surface. Unlike the original formulation where the knots of the first parametric coordinate can evolve arbitrarily with respect to the second coordinate, our formulation designs the knot functions as special curves that guarantee a monotonic blending of the knots corresponding to opposite surface boundaries. Furthermore, we demonstrate that local derivatives on the boundary can be described as an ordinary B-spline surface. The latter property allows for constructing smooth transitions between B-spline boundaries with different knot vectors. [ABSTRACT FROM AUTHOR]

A new way to define mesh importance for decimation uses transfer functions and visualizes large simulation data in cases where normal visualization methods are insufficient due to memory limit. Next, a parallel isosurface simplification framework uses pyramid peeling to extract the decimated meshes progressively without generating the original surface. A new way to define mesh importance for decimation uses transfer functions and visualizes large simulation data in cases where normal visualization methods are insufficient due to memory limits. Next, a parallel isosurface simplification framework uses an importance pyramid to extract and render the decimated meshes progressively without generating the original surface. [ABSTRACT FROM AUTHOR]

Blue noise sampling is an important component in many graphics applications, but existing techniques consider mainly the spatial positions of samples, making them less effective when handling problems with non-spatial features. Examples include biological distribution in which plant spacing is influenced by non-positional factors such as tree type and size, photon mapping in which photon flux and direction are not a direct function of the attached surface, and point cloud sampling in which the underlying surface is unknown a priori. These scenarios can benefit from blue noise sample distributions, but cannot be adequately handled by prior art. Inspired by bilateral filtering, we propose a bilateral blue noise sampling strategy. Our key idea is a general formulation to modulate the traditional sample distance measures, which are determined by sample position in spatial domain, with a similarity measure that considers arbitrary per sample attributes. This modulation leads to the notion of bilateral blue noise whose properties are influenced by not only the uniformity of the sample positions but also the similarity of the sample attributes. We describe how to incorporate our modulation into various sample analysis and synthesis methods, and demonstrate applications in object distribution, photon density estimation, and point cloud sub-sampling. [ABSTRACT FROM AUTHOR]

It is a fundamental problem to calculate Jacobian coefficients of constraint equations in assembly constraint solving because most approaches to solving an assembly constraint system will finally resort to a numerical iterative method that requires the first-order derivatives of the constraint equations. The most-used method of deriving the Jacobian coefficients is to use virtual rotation which is originally presented to derive the equations of motion of constrained mechanical systems. However, when Euler parameters are adopted as the state variables to represent the transformation matrix, using the virtual rotation will yield erroneous formulae of Jacobian coefficients. The reason is that Euler parameters are incompatible with virtual rotation. In this paper, correct formulae of Jacobian coefficients of geometric constraints with respect to Euler parameters are presented in both Cartesian coordinates and relative generalized coordinates. Experimental results show that our proposed formulae make Newton-Raphson iterative method converge faster and more stable. [ABSTRACT FROM AUTHOR]

Assembly data exchange and reuse play an important role in CAD and CAM in shortening the product development cycle. However, current CAD systems cannot transfer mating conditions via neutral file format, and their exported IGES files are heterogeneous. In this paper, a schema for the full data exchange of assemblies is presented based on IGES. We first design algorithms for the pre-and-post processors of parts based on solid model, in which the topologies are explicitly specified and will be referred by mating conditions, and then extend the IGES schema by introducing the Associativity Definition Entity and Associativity Instance Entity defined in IGES standard, so as to represent mating conditions. Finally, a production rule-based method is proposed to analyze and design the data exchange algorithms for assemblies. Within this schema, the heterogeneous representations of assemblies exported from different CAD systems can be processed appropriately, and the mating conditions can be properly exchanged. Experiments on the prototype system verify the robustness, correctness, and flexibility of our schema. [ABSTRACT FROM AUTHOR]

Depth-of-field is one of the most crucial rendering effects for synthesizing photorealistic images. Unfortunately, this effect is also extremely costly. It can take hundreds to thousands of samples to achieve noise-free results using Monte Carlo integration. This paper introduces an efficient adaptive depth-of-field rendering algorithm that achieves noise-free results using significantly fewer samples. Our algorithm consists of two main phases: adaptive sampling and image reconstruction. In the adaptive sampling phase, the adaptive sample density is determined by a 'blur-size' map and 'pixel-variance' map computed in the initialization. In the image reconstruction phase, based on the blur-size map, we use a novel multiscale reconstruction filter to dramatically reduce the noise in the defocused areas where the sampled radiance has high variance. Because of the efficiency of this new filter, only a few samples are required. With the combination of the adaptive sampler and the multiscale filter, our algorithm renders near-reference quality depth-of-field images with significantly fewer samples than previous techniques. [ABSTRACT FROM AUTHOR]

The article talks about an improvement to the stochastic progressive photon mapping (SPPM), a method used to robustly simulate complex global illumination with distributed ray tracing effects, with a Metropolis-Hastings algorithm. It cites the introduction of a well-designed scalar contribution function as the Metropolis sampling strategy aimed at specific parts of image areas with large error to improve the radiance estimator's efficiency. According to experimental results, the robustness of the standard SPPM is being maintained by this new approach.

We propose an adaptive geometry compression method with labels based on four-point interpolatory subdivision schemes. It can work on digital curves of arbitrary dimensions. With the geometry compression method, a digital curve is adaptively compressed into several segments with different compression levels. Each segment is a four-point subdivision curve with a subdivision step. Labels are recorded in data compression to facilitate merging the segments in data decompression. We provide high-speed four-point interpolatory subdivision curve generation methods for efficiently decompressing the compressed data. For an arbitrary positive integer k, formulae for the number of resultant control points of a four-point subdivision curve after k subdivision steps are provided. Some formulae for calculating points at the kth subdivision step are also presented. The time complexity of the new approaches is O(n), where n is the number of points in the given digital curve. Examples are provided to illustrate the efficiency of the proposed approaches. [ABSTRACT FROM AUTHOR]

How to obtain intersection of curves and surfaces is a fundamental problem in many areas such as computer graphics, CAD/CAM, computer animation, and robotics. Especially, how to deal with singular cases, such as tangency or superposition, is a key problem in obtaining intersection results. A method for solving the intersection problem based on the coordinate transformation is presented. With the Lagrange multiplier method, the minimum distance between the center of a circle and a quadric surface is given as well. Experience shows that the coordinate transformation could significantly simplify the method for calculating intersection results. The location of the tangent point is revised according to the tangency condition. It can improve the stability of the intersection of given curves and surfaces in singularity cases. The new algorithm is applied in a three dimensional CAD software (GEMS), produced by Tsinghua University. [ABSTRACT FROM AUTHOR]

A method for computing the visible regions of free-form surfaces is proposed in this paper. Our work is focused on accurately calculating the visible regions of the sequenced rational Bézier surfaces forming a solid model and having coincident edges but no inner-intersection among them. The proposed method calculates the silhouettes of the surfaces without tessellating them into triangle meshes commonly used in previous methods so that arbitrary precision can be obtained. The computed silhouettes of visible surfaces are projected onto a plane orthogonal to the parallel light. Then their spatial relationship is applied to calculate the boundaries of mutual-occlusion regions. As the connectivity of the surfaces on the solid model is taken into account, a surface clustering technique is also employed and the mutual-occlusion calculation is accelerated. Experimental results showed that our method is efficient and robust, and can also handle complex shapes with arbitrary precision. [ABSTRACT FROM AUTHOR]