Abstract We present a machine learning approach for efficiently computing order independent transparency (OIT) by deploying a light weight neural network implemented fully on shaders. Our method is fast, requires a small constant amount of memory (depends only on the screen resolution and not on the number of triangles or transparent layers), is more accurate as compared to previous approximate methods, works for every scene without setup and is portable to all platforms running even with commodity GPUs. Our method requires a rendering pass to extract all features that are subsequently used to predict the overall OIT pixel colour with a pre‐trained neural network. We provide a comparative experimental evaluation and shader source code of all methods for reproduction of the experiments.

Abstract Animation compression is a key process in replicating and streaming animated 3D models. Linear Blend Skinning (LBS) facilitates the compression of an animated sequence while maintaining the capability of real-time streaming by deriving vertex to proxy bone assignments and per frame bone transformations. We introduce a innovative deep learning approach that learns how to assign vertices to proxy bones with persistent labeling. This is accomplished by learning how to correlate vertex trajectories to bones of fully rigged animated 3D models. Our method uses these pretrained networks on dynamic characteristics (vertex trajectories) of an unseen animation sequence (a sequence of meshes without skeleton or rigging information) to derive an LBS scheme that outperforms most previous competent approaches by offering better approximation of the original animation sequence with fewer bones, therefore offering better compression and smaller bandwidth requirements for streaming. This is substantiated by a thorough comparative performance evaluation using several error metrics, and compression/bandwidth measurements. In this paper, we have also introduced a persistent bone labeling scheme that (i) improves the efficiency of our method in terms of lower error values and better visual outcome and (ii) facilitates the fusion of two (or more) LBS schemes by an innovative algorithm that combines two arbitrary LBS schemes. To demonstrate the usefulness and potential of this fusion process, we have combined the outcome of our deep skinning method with that of Rignet—which is a state-of-the-art method that performs rigging on static meshes—with impressive results.

We report on the development of a cutting-edge brain-computer interface (BCI) network that leverages the sensor output of a low cost electroencephalogram (EEG) headband to detect specific eye and head movements, enabling intelligent wheelchair navigation. Using a hybrid CNN-LSTM architecture, our method achieves high accuracy classification of these movements while maintaining low inference time on the complete EEG signal. To validate our approach, we conducted a comprehensive experimental evaluation.

Material aging has a significant effect on the realistic rendering of artwork objects. Small deformations of the surface structure, color or texture variations contribute to the realistic look of artwork objects. These aging effects depend on material composition, object usage, weathering conditions, and a large number of other physical, biological, and chemical parameters. In this work we focus on local deformations due to corrosion/erosion and finally cracks mainly by modeling the behavior of displacements locally. Micro-profilometry provides the quantitative measurements of the surface texture and roughness at micro-metric level, which is used to obtain information about material changes over time in terms of its surface deformation. We present a method for deriving a model for simulating aging based on micro-profilometry measurements taken on material sample plates during an emulated aging process. Subsequently, we use this model for realistic rendering of aged artwork objects.

Depth-sorted fragment determination is fundamental for a host of image-based techniques which simulates complex rendering effects. It is also a challenging task in terms of time and space required when rasterizing scenes with high depth complexity. When low graphics memory requirements are of utmost importance, k-buffer can objectively be considered as the most preferred framework which advantageously ensures the correct depth order on a subset of all generated fragments. Although various alternatives have been introduced to partially or completely alleviate the noticeable quality artifacts produced by the initial k-buffer algorithm in the expense of memory increase or performance downgrade, appropriate tools to automatically and dynamically compute the most suitable value of k are still missing. To this end, we introduce k(+)-buffer, a fast framework that accurately simulates the behavior of k-buffer in a single rendering pass. Two memory-bounded data structures: (i) the max-array and (ii) the max-heap are developed on the GPU to concurrently maintain the k-foremost fragments per pixel by exploring pixel synchronization and fragment culling. Memory-friendly strategies are further introduced to dynamically (a) lessen the wasteful memory allocation of individual pixels with low depth complexity frequencies, (b) minimize the allocated size of k-buffer according to different application goals and hardware limitations via a straightforward depth histogram analysis and (c) manage local GPU cache with a fixed-memory depth-sorting mechanism. Finally, an extensive experimental evaluation is provided demonstrating the advantages of our work over all prior k-buffer variants in terms of memory usage, performance cost and image quality.

k-buffer facilitates novel approaches to multi-fragment rendering and visualization for developing interactive applications on the GPU. Various alternatives have been proposed to alleviate its memory hazards and to avoid completely or partially the necessity of geometry pre-sorting. However, that came with the burden of excessive memory allocation and depth precision artifacts. We introduce k+-buffer, a fast and accurate framework that simulates the k-buffer behavior by exploiting fragment culling and pixel synchronization. Two GPU-accelerated data structures have been developed: (i) the max-array and (ii) the max-heap. These memory-bounded data structures accurately maintain the k-foremost fragments per pixel in a single geometry pass. The choice of the data structure depends on the size k (application-dependent). Without any software-redesign, the proposed scheme can be adapted to perform as a Z-buffer or an A-buffer capturing a single or all generated fragments, respectively. A memory-friendly strategy is also proposed, extending the proposed pipeline to dynamically lessen the potential wasteful memory allocation. Finally, an extensive experimental evaluation is provided demonstrating the advantages of k+-buffer over all prior k-buffer variants in terms of memory usage, performance cost and image quality.

Abstract We present a complete approach to efficiently deriving a varying level‐of‐detail segmentation of arbitrary animated objects. An over‐segmentation is built by combining sets of initial segments computed for each input pose, followed by a fast progressive simplification which aims at preserving rigid segments. The final segmentation result can be efficiently adjusted for cases where pose editing is performed or new poses are added at arbitrary positions in the mesh animation sequence. A smooth view of pose‐to‐pose segmentation transitions is offered by merging the partitioning of the current pose with that of the next pose. A perceptually friendly visualization scheme is also introduced for propagating segment colors between consecutive poses. We report on the efficiency and quality of our framework as compared to previous methods under a variety of skeletal and highly deformable mesh animations.

Many applications require operations on multiple fragments that result from ray casting at the same pixel location. To this end, several approaches have been introduced that process for each pixel one or more fragments per rendering pass, so as to produce a multifragment effect. However, multifragment rasterization is susceptible to flickering artifacts when two or more visible fragments of the scene have identical depth values. This phenomenon is called coplanarity or Z-fighting and incurs various unpleasant and unintuitive results when rendering complex multilayer scenes. In this work, we develop depth-fighting aware algorithms for reducing, eliminating and/or detecting related flaws in scenes suffering from duplicate geometry. We adapt previously presented single and multipass rendering methods, providing alternatives for both commodity and modern graphics hardware. We report on the efficiency and robustness of all these alternatives and provide comprehensive comparison results. Finally, visual results are offered illustrating the effectiveness of our variants for a number of applications where depth accuracy and order are of critical importance.

Abstract In this paper, we present a skeletal rigid skinning approach. First, we describe a skeleton extraction technique that produces refined skeletons appropriate for animation from decomposed character models. Then, to avoid the artifacts generated in previous skinning approaches and the associated high training costs, we develop an efficient and robust rigid skinning technique that applies blending patches around joints. To achieve real time animation, we have adapted all steps of our rigid skinning algorithm so that they are performed efficiently on the GPU. Finally, we present an evaluation of our methods against four criteria: efficiency, quality, scope, and robustness. Copyright © 2010 John Wiley & Sons, Ltd.

Reverse engineering, the process of obtaining a geometric CAD model from measurements obtained by scanning an existing physical model, is widely used in numerous applications, such as manufacturing, industrial design and jewellery design. In this work we propose a framework for reverse engineering objects of freeform design to obtain a fully editable feature-based CAD model that can be reproduced or modified before production. We focus on the process of detecting features on a cloud point and we present a fast method for analyzing the morphology of the surface defined by the point cloud. We compute a point wise characteristic called point concavity intensity and we use this quantity to detect regions that are then refined to object features. The proposed algorithm takes overall O(nlogn) time, where n is the cardinality of the point cloud.

We present ByzantineCAD, a feature-based parametric CAD system for designing pierced Byzantine jewellery. ByzantineCAD is an automated system where jewellery is designed according to the values of parameters and constraints that are determined by the end-user. We introduce an approach to reproducing traditional pierced Byzantine jewellery using pierced voxels ("poxels"). Poxels are voxels with specific attributes and properties that are appropriately combined to create large complex pierced designs. We also present a scaling algorithm for enlarging pierced designs without altering the size of the poxels used to construct them and an algorithm for engraving arbitrary images in pierced jewellery.

We propose a novel approach to shape-based image retrieval that builds upon a similarity criterion which is based on the average point set distance. Compared to traditional techniques, such as dimensionality reduction, our method exhibits better behavior in that it maintains the average topology of shapes independently of the number of points used to represent them and is more resilient to noise. An efficient algorithm is presented based on an incremental "fattening," of the query shape until the best match is discovered. The algorithm uses simplex range search techniques and fractional cascading to provide an average polylogarithmic time complexity on the total number of shape vertices. The algorithm is extended to perform additional fast approximate matching, when there is no image sufficiently similar to the query image. We present techniques for the efficient external storage of the shape base and of the auxiliary geometric data structures used by the algorithm. Finally, we show how our approach can be used for processing queries, containing pairwise relations of object boundaries such as contain, tangent, and overlap. Such queries are either extracted from some user drafted sketch or defined explicitly by the user. Alternative methods are presented for forming query execution plans.

In current distributed systems, the notion of mobility is emerging in many forms and applications. Increasingly many users are not tied to a fixed access point but instead use wireless communications or dial-up services to access data independent of their physical location. Furthermore, mobile software, a popular example being mobile agents, is frequently used as a new form of building distributed network-centric applications. Tracking mobile objects, i.e. identifying their current location, is central to such settings. In this paper, we exploit the use of hierarchical distributed location databases, where each database site covers a specific geographical region and contains location information about all objects residing in it. For highly mobile objects, a scheme based on forwarding pointers enhanced with auxiliary caching techniques is presented, to reduce the cost of the overall network and database traffic generated by frequent location updates. The scheme is extended to support concurrency and failure recovery. Performance is demonstrated through a number of simulation experiments for a range of call to mobility ratios and for a variety of moving and calling behaviors.

To accommodate the increase in user population in future personal communication systems, hierarchical architectures of location databases have been proposed. In this paper, a scheme based on forwarding pointers is presented, that reduces the cost of the overall network and database traffic generated by frequent location updates in such hierarchical architectures. To reduce the number of forwarding pointers that need to be traversed to locate a user, auxiliary caching techniques are presented. Various conditions for purging the chain of forwarding pointers and updating the database are also introduced. Special care is given so that the scheme correctly supports the concurrent execution of updates and lookups. The applicability of the scheme and the performance of the caching techniques are demonstrated through a number of experiments for a range of call to mobility ratios and for a variety of moving and calling behaviors. 1 Introduction Advances in wireless telecommunications and in t...

A graph-constructive approach to solving systems of geometric constraints capable of effeciently handling well-constrained, overconstrained, and underconstrained configurations is presented. The geometric constraint solver works in two phases: in the analysis phase the constraint graph is analyzed and a sequence of elementary construction steps is derived, and then in the construction phase the sequence of construction steps in actually carried out. The analysis phase of the algorithm is described in detail, its correctness is proved, and an efficient algorith to realized it is presented. The scope of the graph analysis is then extended by utilizing semantic information in the form of anlge derivations, and by extending the repertoire of the construction steps. Finally, the construction phase is briefly discussed.

The paper reports on the development of a 2D geometric constraint solver. The solver is a major component of a new generation of cad systems based on a high-level geometry representation. The solver uses a graph-reduction directed algebraic approach, and achieves interactive speed. The paper describes the architecture of the solver and its basic capabilities. Then, it discusses in detail how to extend the scope of the solver, with particular emphasis on the theoretical and human factors involved in finding a solution, in an exponentially large search space, so that the solution is appropriate to the application, and so that the way of finding it is intuitive for an untrained user.