Automatic Texture Mapping Research Articles

TwinTex: Geometry-Aware Texture Generation for Abstracted 3D Architectural Models

Coarse architectural models are often generated at scales ranging from individual buildings to scenes for downstream applications such as Digital Twin City, Metaverse, LODs, etc. Such piece-wise planar models can be abstracted as twins from 3D dense reconstructions. However, these models typically lack realistic texture relative to the real building or scene, making them unsuitable for vivid display or direct reference. In this paper, we present TwinTex , the first automatic texture mapping framework to generate a photorealistic texture for a piece-wise planar proxy. Our method addresses most challenges occurring in such twin texture generation. Specifically, for each primitive plane, we first select a small set of photos with greedy heuristics considering photometric quality, perspective quality and facade texture completeness. Then, different levels of line features (LoLs) are extracted from the set of selected photos to generate guidance for later steps. With LoLs, we employ optimization algorithms to align texture with geometry from local to global. Finally, we fine-tune a diffusion model with a multi-mask initialization component and a new dataset to inpaint the missing region. Experimental results on many buildings, indoor scenes and man-made objects of varying complexity demonstrate the generalization ability of our algorithm. Our approach surpasses state-of-the-art texture mapping methods in terms of high-fidelity quality and reaches a human-expert production level with much less effort.

AUTOMATIC TEXTURE MAPPING METHOD FOR 3D MODELS TO CIRCUMVENT OCCLUSION THROUGH 3D SPATIAL THROUGH-VIEW RELATIONSHIPS BETWEEN IMAGES,MODELS, AND POINT CLOUDS

Abstract. Photorealistic 3D models play an important role in various applications related to smart cities. Texture mapping plays a crucial role as the last step of 3D reconstruction. The texture of the model directly reflects the visualization and realism of the model. In complex city scenes, objects often have varying degrees of occlusion from one another. Traditional methods to circumvent occlusion by image or model data are not very effective. In this paper, we propose an automatic texture mapping method for 3D models to circumvent occlusion through 3D spatial through-view relationships between images, models, and point clouds. First of all, calculate the density and voxel resolution of the point clouds, the point clouds here can be either dense matching point clouds or laser point clouds. Voxelization is based on point clouds, voxels generated by voxelization can reflect the spatial location of the point clouds. Secondly, to determine whether there is an occlusion of voxels between the image and the model vertices based on the spatial through-view relationship between the image, the model, and the voxels, and filter out the unobstructed images. Finally, by optimizing the data items of the Markov random field, the shading function is added to the original data items for evaluating the shading condition, based on which the most suitable image is selected for texture mapping of a triangular surface of the model. Loop computation to complete the unobstructed texture mapping of the entire model. In this paper, the public test datasets released by the International Society for Photogrammetry and Remote Sensing (ISPRS) and several urban area datasets collected by ourselves are incorporated to test the performance of the proposed method. Both qualitative and quantitative cross-sectional comparisons with existing texture mapping algorithms are conducted and presented. Experimental results indicate that our method can effectively circumvent occlusion for automated texture mapping, and generate 3D models with fewer obstructed textures, which largely improves the visual quality and realism of the models.

TO ACHIEVE REAL IMMERSION: THE 3D VIRTUAL AND PHYSICAL RECONSTRUCTION OF CAVE 3 AND CAVE 12 OF YUNGANG GROTTOES

Abstract. As the 3D laser scanning and photogrammetry technologies continue to mature, more and more applications founded in numerous areas. The realistic 3D models are mainly adopted for digital display uses, such as the 3D game, web showcases, head-mounted display, etc. While we are enjoying the vivid digital sceneries through different kinds of digital display screens, there are still challenges exist for the 3D printing application, especially for large size objects. In this article, we will present an approach on digitizing and 3D replicating large grottoes. Unlike 3D rendering, 3D printing requires high detailed shape data for the fabrication. Such demands cause many technical difficulties including huge data amount, accurate dense point cloud, high-resolution texture mapping. We chose cascade SfM, grouped MVS, automatic texture mapping to prepare the high definition colored 3D model for printing and painting references. Meanwhile, we optimized 3D printing procedure as well as post-processing, installation, lacquer and painting. Two replicas of 10- meter sized grottoes have been manufactured after four years of efforts, which have earned some appreciations from audiences.

STUDY ON PRACTICAL TECHNOLOGIES OF AERIAL TRIANGULATION FOR REAL SCENE 3D MOELING WITH OBLIQUE PHOTOGRAPHY

Abstract. The key technologies in the real scene 3D modeling of oblique photography mainly include the data acquisition of oblique photography, layout and surveying of photo control points, oblique camera calibration, aerial triangulation, dense matching of multi-angle image, building of triangulation irregular network (TIN) and TIN simplification and automatic texture mapping, among which aerial triangulation is the core and the results of aerial triangulation directly affect the later model effect and the corresponding data accuracy. Starting from this point of view, this paper aims to study the practical technologies of aerial triangulation for real scene 3D modeling with oblique photography and finally proposes a technical method of aerial triangulation with oblique photography which can be put into practice.

网络三维虚拟校园仿真平台构建

基于三维可视化、计算机网络等技术，实现校园室内外一体化三维虚拟仿真平台构建与发布。通过师院二维校园平面图，结合遥感影像数据，依据真实校园场景布局进行三维场景建模。基于CityEngine的CGA (Computer Generated Architecture)规则语言进行的校园三维场景构建，实现建筑物模型的快速生成和纹理自动映射，以及室内场景与行人、车俩、动态水和标志性建筑物等特殊模型的快速构建。同时，将摄像头等多源时空数据与校园管理系统接入三维校园平台，实现各教学楼属性信息和安防多媒体信息的展现与查询。此外，通过自动漫游等功能可对校园进行多方位展示。 Based on the technologies such as 3D visualization, computer network and so on, the establish-ment and publishment of campus indoor and outdoor integration 3D virtual simulation platform have been achieved. Through the 2D campus plan of the Guangxi Teachers Education University, combined with remote sensing image data, 3D scene is modeled according to the real campus scene layout. Campus 3D scene construction, based on CGA (Computer Generated Architecture) rule language of City Engine, has achieved the rapid generation of building models and automatic texture mapping, as well as the rapid construction of indoor scenes and pedestrians, cars, dynamic water, landmark buildings and other special models. At the same time, the multi-source spatio-temporal data such as camera and campus management system are connected into 3D campus platform so that the display and inquiry of the attribute information of teaching buildings and security multimedia information can be achieved. In addition, the campus can be displayed in different directions through functions such as automatic roaming.

Isosurface rendering of medical images improved by automatic texture mapping

Advances in medical imaging modalities have allowed the acquisition of large collections of volumetric images for clinical and training purposes, such as Computerized Tomography, Magnetic Resonance Imaging, Mammography, Fluoroscopy, X-Ray Microtomography, Positron Emission Tomography and Ultrasonography. Volume rendering has proved to be a very flexible and effective technique for exploring and visualizing such massive medical data sets. Realistic models of complex human anatomical structures can be constructed and manipulated by medical professionals to enhance internal structures of interest. This work proposes and evaluates a novel isosurface rendering method for medical images improved by automatic texture mapping. The texture information is generated through different volume projection approaches. Experiments conducted on several data sets demonstrate the effectiveness of the proposed rendering method.

AUTOMATIC TEXTURE MAPPING OF ARCHITECTURAL AND ARCHAEOLOGICAL 3D MODELS

Abstract. Today, detailed, complete and exact 3D models with photo-realistic textures are increasingly demanded for numerous applications in architecture and archaeology. Manual texture mapping of 3D models by digital photographs with software packages, such as Maxon Cinema 4D, Autodesk 3Ds Max or Maya, still requires a complex and time-consuming workflow. So, procedures for automatic texture mapping of 3D models are in demand. In this paper two automatic procedures are presented. The first procedure generates 3D surface models with textures by web services, while the second procedure textures already existing 3D models with the software tmapper. The program tmapper is based on the Multi Layer 3D image (ML3DImage) algorithm and developed in the programming language C++. The studies showing that the visibility analysis using the ML3DImage algorithm is not sufficient to obtain acceptable results of automatic texture mapping. To overcome the visibility problem the Point Cloud Painter algorithm in combination with the Z-buffer-procedure will be applied in the future.

3D HERITAGE DOCUMENTATION

Nowadays, realistic 3D models are achieved from high resolution texture warped to laser scanner meshes. Multiple photos are normally required for texture mapping, so many manual processes have to be implemented which are absolutely time consuming especially in large sites. The challenge is to handle these processes automatically by developing suitable algorithms. Therefore we focus here on a developed algorithm for automatic texture mapping with its corresponding software. The recent techniques are then used to recover a complete 3D model for paintings inside the Domitilla catacomb which is the largest catacomb in Rome. Such models will help archaeologists to virtually reach the catacomb without putting their feet underground and accordingly conduct their own research

Automatic Texture Mapping Algorithm for Plant Leaf Model

Texture mapping of plant leaf is a challenging task because of the shape diversity. Based on the barycentric mapping parameterization method, a novel algorithm is proposed. A suitable boundary mapping is computed by automatically extracting and matching the feature points on boundaries of the mesh and image. The matching process consists of two steps, which utilize the symmetry and curvature information respectively. Through iteratively minimizing a weighted energy, the inner constraints given by users in order to make the details clearer can be satisfied by the presented algorithm. Experiments show that this robust algorithm can produce plant leaves with fine texture details and increase the realism of the models.

A minimal and complete set of operators for the development of robust manifold mesh modelers

In this paper, we identify a minimal and complete set of fundamental operators, which is necessary and sufficient for performing all homeomorphic and topological operations on 2-manifold mesh structures. Efficient algorithms are developed for the implementation of these operators. We also developed a set of powerful, user-friendly, and effective operators at the level of user-interface. Using these operators, we have developed a prototype system for robust, interactive, and user-friendly modeling of orientable 2-manifold meshes. Users of our system can perform a large set of homeomorphic and topological changes with these user-interface level operators. Our system is topologically robust in the sense that users will never create invalid 2-manifold mesh structure with these operators. In our system, the homeomorphic and topological surgery operations can be applied alternatively on 2-manifold meshes. With our system, users can blend surfaces, construct rinds, and open holes on these rind shapes. With our system, the shapes that look like solid, non-manifold, or 2-manifold with boundary can be manipulated. The system also provides automatic texture mapping during topology changes.

Fast head modeling for animation

This paper describes an efficient method to make individual faces for animation from several possible inputs. We present a method to reconstruct a three-dimensional (3D) facial model for animation from two orthogonal pictures taken from front and side views, or from range data obtained from any available resources. It is based on extracting features on a face in a semiautomatic way and modifying a generic model with detected feature points. Then fine modifications follow if range data is available. Automatic texture mapping is employed using an image composed from the two images. The reconstructed 3D-face can be animated immediately with given expression parameters. Several faces by obtained one methodology applied to different input data to get a final animatable face are illustrated.