Search

Recently, there has been renewed interest in signed distance bound representations due to their unique properties for 3D shape modelling. This is especially the case for deep learning-based bounds. However, it is beneficial to work with polygons in most computer graphics applications. Thus, in this paper, we introduce and investigate an asymptotically fast method for transforming signed distance bounds into polygon meshes. This is achieved by combining the principles of sphere tracing (or ray marching) with traditional polygonization techniques, such as marching cubes. We provide theoretical and experimental evidence that this approach is of the O (N 2 log N) computational complexity for a polygonization grid with N 3 cells. The algorithm is tested on both a set of primitive shapes and signed distance bounds generated from point clouds by machine learning (and represented as neural networks). Given its speed, implementation simplicity, and portability, we argue that it could prove useful during the modelling stage as well as in shape compression for storage. [ABSTRACT FROM AUTHOR]

As we know, image colorization is widely used in computer graphics and has become a research hotspot in the field of image processing. Current image colorization technology has the phenomenon of single coloring effect and unreal color, which is too complicated to be implemented and struggled to gain popularity. In this paper, a new method based on a convolution neural network is proposed to study the reasonable coloring of human images and ensures the realism of the coloring effect and the diversity of coloring at the same time. First, this paper selects about 5000 pictures of people and plants from the Imagenet dataset and makes a small dataset containing only people and backgrounds. Secondly, in order to obtain the image segmentation results, this paper improves the U-net network and carries out three times of down sampling and three times of up-sampling. Finally, we add the expanded convolution, and use the sigmoid activation function to replace the ReLU (The Rectified Linear Unit) activation function and put the BN (Batch Normalization) before the activation function. Experimental results show that our proposed image colorization algorithm based on the deep learning scheme can reduce the training time of the network and achieve higher quality segmentation results. [ABSTRACT FROM AUTHOR]

Clipping has great importance in computer graphics. the clip window is generally of rectangular shape but it may be in any shape. for rectangular clip window we have many popular algorithms like Cohan-Sutherland algorithm. Cyrus Beck algorithm. Liang Barsky algorithms, but it is not necessary that clip window will be always in shape of rectangle it may be of any type of convex region. One of the most common geometrical entities is circle if clip window is in circular shape, then how clipping can be done? How we can identify the position of line segment with respect to circular clip window? Thi paper presents a simple algorithm using parametric equation of the line to determine the position of the line with respect to the circular clip window and discuss the method to clip the clipping candidate line. The proposed algorithm is very simple and less computationally expensive. [ABSTRACT FROM AUTHOR]

Currently, there is less research on how to improve the efficiency of the application of computer graphics technology in the creation of public sculpture. Therefore, this paper will focus on how computer graphics algorithms can enable systems for the creation of public sculpture with the intervention of computer graphics technology to create more accurate and completed works of public sculpture. It will explore and analyze how computer image algorithms can help creators apply computer image technology to finish complete and accurate public sculptures, and individual studies, computer imagery, and model analysis are also used. In systems for the creation of public sculpture, the point cloud data of the model is obtained through 3D laser scanning technology; then the algorithm of the point cloud model is integrated and the Statistical Outlier Removal algorithm of the point cloud model intervention is processed. By this way, the point cloud model of the work is optimized, and then a more completed and accurate public sculpture work can be produced by 3D sculpting or 3D printing. The research shows that, in the creation of public sculptures with the intervention of computer graphics technology, the computer graphics algorithm acquires the basis of the high-definition public sculpture data model. The computer graphics algorithm improves the accuracy and completeness of the creator using computer graphics technology; it is also the key to transform the accurate enlargement and transformation of the sculptural model into the actual sculptural work. [ABSTRACT FROM AUTHOR]

Due to advances in high-performance computing technologies, computer graphics techniques—especially those related to mesh simplification—have been noticeably improved. These techniques, which have a strong impact on many applications, such as geometric modeling and visualization, have been well studied for more than two decades. Recent advances in GPUs have led to significant improvements in terms of speed and interactivity. In this paper, we present a mesh simplification algorithm that benefits from the parallel framework provided by recent GPUs. We customize the halfedge data structure for adaption with the dynamic memory restrictions of CUDA. The proposed algorithm is fully parallelized by employing a lock-free skip priority queue and a set of disjoint regions of the mesh. The proposed technique accelerates the simplification process while preserving the topological properties of the mesh. Some results and comparisons are provided to verify the efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The visual appearance of materials depends on their intrinsic light transfer properties, the illumination and camera conditions, and other environmental factors. This is in particular the case of porous, rough, or absorbent materials, where the presence of liquid on the surface alters significantly their BRDF, which in turn results in considerable changes in their visual appearance. For this reason, rendering materials change their appearance when wet continues to be a relevant topic in computer graphics. This is especially true when real-time photo-realistic rendering is required in scenes involving this kind of materials in interaction with water or other liquids. In this paper, we introduce a physically inspired technique to model and render appearance changes of absorbent materials when their surface is wet. First, we develop a new method to solve the interaction between the liquid and the object surface using its own underlying texture coordinates. Then, we propose an algorithm to model the diffusion phenomenon that occurs in the interface between a solid porous object and a liquid. Finally, we extend a model that explains the change of appearance of materials under wet conditions, and we implement it achieving real-time performance. The complete model is developed using GPU acceleration. [ABSTRACT FROM AUTHOR]

Summary: Stable image matching is still a pursuit goal in the communities of computer vision and graphics because of many potential applications such as 3D reconstruction, object recognition, and visual tracking. In the case of 3D reconstruction, modern structure‐from‐motion methods depend heavily on image‐matching methods for recovering geometric models. Existing methods have tried to exploit various strategies to generate correct feature correspondences for 3D reconstruction. However, there are no efficient methods that can work well in the wild. To defend this drawback, in this paper, we design a stable image‐matching method for 3D reconstruction. The method consists of feature point detection, descriptor extraction, feature matching, and matching verification. Besides, we try to choose a stable algorithm for each module of the proposed method, in which the adopted algorithms are implemented in an optimized approach for acceleration. Finally, we conduct a systematic experiment on several benchmarking datasets to assess the performance of the proposed method. Experimental results show that the proposed method has both high matching precision and fast speed. [ABSTRACT FROM AUTHOR]

NURBS method is the standard mathematical method for describing the shapes of curves/surfaces/volumes, and it is extensively used in computer-aided design, computer-aided manufacturing, and computer graphics. The injectivity of NURBS volumes means that they do not have self-intersections. Since the injectivity of parameterizations depend on the signs of their Jacobian functions, and the Jacobian of a NURBS volume is determined by the determinant of its tangent vectors in three directions, we first propose a method to compute the bounding vectors of the tangent cones of NURBS volume in this paper. Then the sufficient condition for the injectivity of NURBS volume is proposed. A checking algorithm is also presented. Some examples are given to verify the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

A crossover refers to the intersection of two satellite ground tracks. Crossovers are required for performing crossover differences adjustment to remove the orbit error and for establishing the time series of elevation in surfaces, which is why crossovers are important for satellite altimetry measurements of ice sheet or ice shelf elevation changes. How to extract more crossovers precisely is the objective of this paper. On the basis of the traditional method of solving crossovers and computer graphics, this paper proposes an improved algorithm called improved rapid rejection and straddle test (IRST) for computing the position of the crossover point. This algorithm efficiently and accurately searches for two points in ascending pass and two points in descending pass that can form a crossover, and then computes crossovers' geolocation. By using CryoSat-2 satellite altimeter data, we conducted our study on the Antarctic Ross ice shelf and Filchner–Ronne ice shelf using the fixed iteration (FI) algorithm, rapid rejection and straddle test (RST) algorithm, and the IRST algorithm. Results show that IRST is superior to the two other algorithms in terms of the number of crossovers, geolocation accuracy and computational efficiency. These advantages are more noticeable in the border areas between the ice shelf and the mountain with large terrain slope, which solves the problem that crossovers are less in these areas with poor-quality data coverage. • The improved algorithm computes more crossover points efficiently. • Crossover points computed by the improved algorithm with high geolocation accuracy. • More crossover points cover on the steep areas using the improved algorithm. [ABSTRACT FROM AUTHOR]

• In the paper we propose a novel approach for solving puzzles whose pieces are of general shape, which need not necessarily match precisely due to erosion, and which have degraded unevenly over time. • We define the notion of valid transformations and propose a method of sampling them. This method may find uses in other domains. • We define a novel dissimilarity score that takes into account the special characteristics of the domain. • We introduce the notion of confidence in the dissimilarity scores, which depends not only on the value of the dissimilarity, but also on those of the competing matches. Confidence may be used not only in re-assembly, but also in other applications that are based on dissimilarity. This paper focuses on the re-assembly of an archaeological artifact, given images of its fragments. This problem can be considered as a special challenging case of puzzle solving. The restricted case of re-assembly of a natural image from square pieces has been investigated extensively and was shown to be a difficult problem in its own right. Likewise, the case of matching "clean" 2D polygons/splines based solely on their geometric properties has been studied. But what if these ideal conditions do not hold? This is the problem addressed in the paper. Three unique characteristics of archaeological fragments make puzzle solving extremely difficult: (1) The fragments are of general shape; (2) They are abraded, especially at the boundaries (where the strongest cues for matching should exist); and (3) The domain of valid transformations between the pieces is continuous. The key contribution of this paper is a fully-automatic and general algorithm that addresses puzzle solving in this intriguing domain. We show that our approach manages to correctly reassemble dozens of broken artifacts and frescoes. [ABSTRACT FROM AUTHOR]

Voxel-based data structures, algorithms, frameworks, and interfaces have been used in computer graphics and many other applications for decades. There is a general necessity to seek adequate digital representations, such as voxels, that would secure unified data structures, multi-resolution options, robust validation procedures and flexible algorithms for different 3D tasks. In this review, we evaluate the most common properties and algorithms for voxelisation of 2D and 3D objects. Thus, many voxelisation algorithms and their characteristics are presented targeting points, lines, triangles, surfaces and solids as geometric primitives. For lines, we identify three groups of algorithms, where the first two achieve different voxelisation connectivity, while the third one presents voxelisation of curves. We can say that surface voxelisation is a more desired voxelisation type compared to solid voxelisation, as it can be achieved faster and requires less memory if voxels are stored in a sparse way. At the same time, we evaluate in the paper the available voxel data structures. We split all data structures into static and dynamic grids considering the frequency to update a data structure. Static grids are dominated by SVO-based data structures focusing on memory footprint reduction and attributes preservation, where SVDAG and SSVDAG are the most advanced methods. The state-of-the-art dynamic voxel data structure is NanoVDB which is superior to the rest in terms of speed as well as support for out-of-core processing and data management, which is the key to handling large dynamically changing scenes. Overall, we can say that this is the first review evaluating the available voxelisation algorithms for different geometric primitives as well as voxel data structures. [ABSTRACT FROM AUTHOR]