Generating a Texture Map from Object-Surface Texture Data

A number of 3D digitizing methods, including stereopsis, are capable of measuring not only an object's shape but also its surface texture. Measured shape data can be expressed as a polyhedron whose faces are triangular, and object-surface texture data can be represented in the form of color data for each of the vertices of the various triangles. The ability to apply object-surface texture data directly to the creation of computer graphics images has been severely limited by the extreme difficulty of expressing such texture data in the image from which conventional texture mapping proceeds (commonly referred to as a texture map). Proposed here is a method that generates a texture map from object-surface texture data. First, the method reduces the number of triangles in the polyhedron while preserving essentially all the color data that it originally contained. Next, it arranges the triangles in the simplified triangle mesh onto a plane, and generates a texture map from this arrangement. This method preserves the full texture of an object, no matter how complex its shape, an advantage over the conventional cylindrical texture representation approach. Furthermore, since essentially all color data has been retained, the reduction in the number of triangles does not produce any significant reduction in the texture-realism of the object image produced.     

PC-based Real-time Texture Painting on Real World Objects

The problem of texture mapping on real world objects has attracted attention^11,8 recently. A work by Lensch et al. ⁹ addressed the problem of locating a camera position in the celestial sphere and then mapping the acquired pictures on a real world object. The entire process took a half hour to one hour to map 10 to 15 pictures. In this paper, we propose a new innovative algorithm to speed up the texture mapping or painting process in real-time. We built a PC-based system using a commonly available video card with a geometry engine. Mapping of a picture required about 20 seconds. It is successful in giving an illusion to the operator to paint a colorless real world object with a color texture brush.     

ℒ0 Gradient‐Preserving Color Transfer

This paper presents a new two‐step color transfer method which includes color mapping and detail preservation. To map source colors to target colors, which are from an image or palette, the proposed similarity‐preserving color mapping algorithm uses the similarities between pixel color and dominant colors as existing algorithms and emphasizes the similarities between source image pixel colors. Detail preservation is performed by an ?0 gradient‐preserving algorithm. It relaxes the large gradients of the sparse pixels along color region boundaries and preserves the small gradients of pixels within color regions. The proposed method preserves source image color similarity and image details well. Extensive experiments demonstrate that the proposed approach has achieved a state‐of‐art visual performance.     

Compression-Based 3D Texture Mapping for Real-Time Rendering

While 2D texture mapping is one of the most effective of the rendering techniques that make 3D objects appear visually interesting, it often suffers from visual artifacts produced when 2D image patterns are wrapped onto the surfaces of objects with arbitrary shapes. On the other hand, 3D texture mapping generates highly natural visual effects in which objects appear carved from lumps of materials rather than laminated with thin sheets as in 2D texture mapping. Storing 3D texture images in a table for fast mapping computations, instead of evaluating procedures on the fly, however, has been considered impractical due to the extremely high memory requirement. In this paper, we present a new effective method for 3D texture mapping designed for real-time rendering of polygonal models. Our scheme attempts to resolve the potential texture memory problem by compressing 3D textures using a wavelet-based encoding method. The experimental results on various nontrivial 3D textures and polygonal models show that high compression rates are achieved with few visual artifacts in the rendered images and a small impact on rendering time. The simplicity of our compression-based scheme will make it easy to implement practical 3D texture mapping in software/hardware rendering systems including real-time 3D graphics APIs such as OpenGL and Direct3D.     

一种利用附加纹理信息进行三维喷绘的方法

针对三维透视投影视图中对三维物体表面纹理直接进行喷绘,以获得复杂纹理图这一计算机图形交互技术这一新问题,研究了一种将纹理图的象素位置信息转换成彩色信息,然后利用纹理映射将纹理坐标连同该点上的颜色值一起传递到与屏幕象素对应的可见点上的方法,其中颜色值依该点处的入射光线方向和表面法向被进一步转换为光强值,而纹理坐标则被解码后还原成与该可见点对应的纹理坐标,被存入信息缓冲器中,供以后使用,通过解码,可根据屏幕点直接得到纹理象素点的坐标,经过算法优化,实现了对三维物体表面纹理的实时喷绘;同时阐述了在三维图象生成技术中使用附加纹理信息的应用实例以及相关定义。     

Texture mapping on surfaces of arbitrary topology using norm preserving-based optimization

A simple and yet highly efficient, high-quality texture mapping method for surfaces of arbitrary topology is presented. The new method projects the given surface from the 3D object space into the 2D texture space to identify the 2D texture structure that will be used to texture the surface. The object space to texture space projection is optimized to ensure minimum distortion of the texture mapping process. The optimization is achieved through a commonly used norm preserving minimization process on edges of the surface. The main difference here is, by using an initial value approach, the optimization problem can be set up as a quadratic programming problem and, consequently, solved by a linear least squares method. Three methods to choose a good initial value are presented. Test cases show that the new method works well on surfaces of arbitrary topology, with the exception of surfaces with exceptionally abnormal curvature distribution. Other advantages of the new method include uniformity and seamlessness of the texture mapping process. The new method is suitable for applications that do not require precise texture mapping results but demand highly efficient mapping process such as computer animation or video games.     

Global Texture Mapping for Dynamic Objects

We propose a novel framework to generate a global texture atlas for a deforming geometry. Our approach distinguishes from prior arts in two aspects. First, instead of generating a texture map for each timestamp to color a dynamic scene, our framework reconstructs a global texture atlas that can be consistently mapped to a deforming object. Second, our approach is based on a single RGB‐D camera, without the need of a multiple‐camera setup surrounding a scene. In our framework, the input is a 3D template model with an RGB‐D image sequence, and geometric warping fields are found using a state‐of‐the‐art non‐rigid registration method [GXW*15] to align the template mesh to noisy and incomplete input depth images. With these warping fields, our multi‐scale approach for texture coordinate optimization generates a sharp and clear texture atlas that is consistent with multiple color observations over time. Our approach is accelerated by graphical hardware and provides a handy configuration to capture a dynamic geometry along with a clean texture atlas. We demonstrate our approach with practical scenarios, particularly human performance capture. We also show that our approach is resilient on misalignment issues caused by imperfect estimation of warping fields and inaccurate camera parameters.     

Texture mapping and distortion in digital graphics

Texture mapping is a method commonly used to increase the visual complexity of computer generated images while maintaining simplicity in the underlying geometric models. Texture maps are generally defined in two dimensional space; thus, a primary problem when applying textures to objects is determining a mapping transformation from the three dimensional space of the object to the two dimensional space of the map. A method for mapping complex polygonal geometries is presented. The algorithmunfolds the object polygon by polygon and projects the texture map onto the resulting two dimensional geometry. Enhancements to the basic unfolding algorithm either (1) control the location of map distorition introduced at areas of severe curvature or (2) average distortions over a larger area.     

Learning Style Compatibility Between Objects in a Real‐World 3D Asset Database

Large 3D asset databases are critical for designing virtual worlds, and using them effectively requires techniques for efficient querying and navigation. One important form of query is search by style compatibility: given a query object, find others that would be visually compatible if used in the same scene. In this paper, we present a scalable, learning‐based approach for solving this problem which is designed for use with real‐world 3D asset databases; we conduct experiments on 121 3D asset packages containing around 4000 3D objects from the Unity Asset Store. By leveraging the structure of the object packages, we introduce a technique to synthesize training labels for metric learning that work as well as human labels. These labels can grow exponentially with the number of objects, allowing our approach to scale to large real‐world 3D asset databases without the need for expensive human training labels. We use these synthetic training labels in a metric learning model that analyzes the in‐engine rendered appearance of an object—combining geometry, material, and texture—whereas prior work considers only object geometry, or disjoint geometry and texture features. Through an ablation experiment, we find that using this representation yields better results than using renders which lack texture, materiality, or both.     

Ground object recognition and segmentation from aerial image‐based 3D point cloud

Several attempts have been made to grasp three‐dimensional (3D) ground shape from a 3D point cloud generated by aerial vehicles, which help fast situation recognition. However, identifying such objects on the ground from a 3D point cloud, which consists of 3D coordinates and color information, is not straightforward due to the gap between the low‐level point information (coordinates and colors) and high‐level context information (objects). In this paper, we propose a ground object recognition and segmentation method from a geo‐referenced point cloud. Basically, we rely on some existing tools to generate such a point cloud from aerial images, and our method tries to give semantics to each set of clustered points. In our method, firstly, such points that correspond to the ground surface are removed using the elevation data from the Geographical Survey Institute. Next, we apply an interpoint distance‐based clustering and color‐based clustering. Then, such clusters that share some regions are merged to correctly identify a cluster that corresponds to a single object. We have evaluated our method in several experiments in real fields. We have confirmed that our method can remove the ground surface within 20 cm error and can recognize most of the objects.     

Real‐time Rendering of Heterogeneous Translucent Objects with Arbitrary Shapes

We present a real‐time algorithm for rendering translucent objects of arbitrary shapes. We approximate the scattering of light inside the objects using the diffusion equation, which we solve on‐the‐fly using the GPU. Our algorithm is general enough to handle arbitrary geometry, heterogeneous materials, deformable objects and modifications of lighting, all in real‐time. In a pre‐processing step, we discretize the object into a regular 4‐connected structure (QuadGraph). Due to its regular connectivity, this structure is easily packed into a texture and stored on the GPU. At runtime, we use the QuadGraph stored on the GPU to solve the diffusion equation, in real‐time, taking into account the varying input conditions: Incoming light, object material and geometry. We handle deformable objects, provided the deformation does not change the topological structure of the objects.     

虚平面映射:深度图像内部视点的绘制技术

首先推导与归纳了图像三维变换中像素深度场的变换规律,同时提出了基于深度场和极线原则的像素可见性别方法,根据上述理论和方法,提出一种基于深度图像的建模与绘制(image-based modeling and rendering,简称IBMR)技术,称为虚平面映射.该技术可以基于图像空间内任意视点对场景进行绘制.绘制时,先在场景中根据视线建立若干虚拟平面,将源深度图像中的像素转换到虚平面上,然后通过对虚平面上像素的中间变换,将虚平面转换成平面纹理,再利用虚平面的相互拼接,将视点的成像以平面纹理映射的方式完成.新方法还能在深度图像内侧,基于当前视点快速获得该视点的全景图,从而实现视点的实时漫游.新方法视点运动空间大、存储需求小,且可以发挥图形硬件的纹理映射功能,并能表现物体表面的三维凹凸细节和成像视差效果,克服了此前类似算法的局限和不足.     

Calculus of nonrigid surfaces for geometry and texture manipulation

We present a geometric framework for automatically finding intrinsic correspondence between three-dimensional nonrigid objects. We model object deformation as near isometries and find the correspondence as the minimum-distortion mapping. A generalization of multidimensional scaling is used as the numerical core of our approach. As a result, we obtain the possibility to manipulate the extrinsic geometry and the texture of the objects as vectors in a linear space. We demonstrate our method on the problems of expression-invariant texture mapping onto an animated three-dimensional face, expression exaggeration, morphing between faces, and virtual body painting.     

带不失真纹理映射的三维Morphing动画研究及实现

介绍了三维Morphing，编程实现了相同顶点数和拓扑结构的物体之间的Morphing，并采用一种带不失真纹理映射的船形曲面造型法，有效地消除了形变曲面的纹理映射的图像失真问题，最后给出了基于任意拓扑结构的物体间Morphing的方法。     

A randomized algorithm for natural object colorization

Natural objects often contain vivid color distribution with wide variety of colors. Conventional colorization techniques, on the other hand, produce colors that are relatively flat with little color variation. In this paper, we introduce a randomized algorithm which considers not only the value of target color but also the distribution of target color. In essence, our algorithm paints a color distribution to a region which synthesizes color distribution of a natural object. Our approach models the correlation between intensity and color in HSV color space in terms of H – S, H – V and S – V joint histogram. During the colorization process, we randomly swap and reassign color of a pixel to minimize a cost function that measures color consistency to its neighborhood and intensity‐to‐color correlation captured in the joint histogram. We tested our algorithm extensively on many natural objects and our user study confirms that our results are more vivid and natural compared to results from previous techniques.     

Texture Mapping with Hard Constraints

We show how to continuously map a texture onto a 3D triangle mesh when some of the mesh vertices are constrained to have given ( u , v ) coordinates. This problem arises frequently in interactive texture mapping applications and, to the best of our knowledge, a complete and efficient solution is not available. Our techniques always guarantee a solution by introducing extra (Steiner) vertices in the triangulation if needed. We show how to apply our methods to texture mapping in multi-resolution scenarios and image warping and morphing.     

Solid Texturing of Soft Objects

Since the shape of a soft object changes in response to its surroundings, it is difficult to give a single position in space as the location of the object. Indeed objects can and do break dynamically into subobjects. This means that you cannot map a solid texture onto such an object simply by using a function of the space coordinates. We have taken a different approach. Our soft objects are modeled as the volume enclosed by an isosurf ace of a field calculated from a set of key points. For each key point, we describe an abstract texture space. Any point on the surface of an object has, associated with each key point, a position in this space and a field contribution. A vector sum of these positions, weighted by the field contributions, is used to select a surface specification from the texture space. Textures mapped with this process retain their consistency during distortion and metamorphoses of objects, permitting a great variety of animation effects.     

Solid texture synthesis for heterogeneous translucent materials

We present a method to synthesize solid textures from heterogeneous translucent materials that have a complex pattern and subsurface scattering effect. A solid texture provides consistent texture throughout the volume, so that it can be used to model the texture on an arbitrary geometry. However, solid texture synthesis requires a huge amount of time to generate the volume. Moreover, a synthesized solid texture acquires only the color information from an input exemplar. Therefore, it has been difficult to render the appearance of a translucent object realistically without additional appearance data. In this paper, we introduce a new search method to accelerate synthesizing of solid textures. This method decomposes the candidates in an exemplar into several subgroups and searches for the best similar neighborhood in each decomposed subgroup. We also apply subsurface scattering effects to the shell layer of a synthesized object for realistic rendering of a translucent solid texture. Experimental results show that our rendering method can produce realistic rendering results for various heterogeneous translucent objects. It can also represent cross-sections of an object realistically without reconstructing the texture and surface geometry.     

Visual saliency guided textured model simplification

Mesh geometry can be used to model both object shape and details. If texture maps are involved, it is common to let mesh geometry mainly model object shapes and let the texture maps model the most object details, optimising data size and complexity of an object. To support efficient object rendering and transmission, model simplification can be applied to reduce the modelling data. However, existing methods do not well consider how object features are jointly represented by mesh geometry and texture maps, having problems in identifying and preserving important features for simplified objects. To address this, we propose a visual saliency detection method for simplifying textured 3D models. We produce good simplification results by jointly processing mesh geometry and texture map to produce a unified saliency map for identifying visually important object features. Results show that our method offers a better object rendering quality than existing methods.     

Photogrammetric reconstruction of free-form objects with curvilinear structures

The shapes of many natural or man-made objects have curve features. The images of such curves usually do not have sufficient distinctive features to apply conventional feature-based reconstruction algorithms. In this paper, we introduce a photogrammetric method for recovering free-form objects with curvilinear structures. Our method chooses to obtain the topology and geometry of a sparse 3D wireframe of the object first instead of directly recovering a surface or volume model. Surface patches covering the object are then constructed to interpolate the curves in this wireframe while satisfying certain heuristics such as minimal bending energy. The result is an object surface model with curvilinear structures from a sparse set of images. We can produce realistic texture-mapped renderings of the object model from arbitrary viewpoints. Reconstruction results on multiple real objects are presented to demonstrate the effectiveness of our approach.