Model-based coding of multiviewpoint imagery

Differing from common 2D images, a texture map, since it is used to project onto a 3D model in 3D space, not only contains 2D texture information, but also implicitly associates certain 3D geometric information. Related to this, an effective 3D geometry-dependent texture map compression method with hybrid region of interest (ROI) coding is proposed in this paper. We regard the visually important area of the texture map as the ROI. To acquire the visually important areas of the texture map, we take into account information from both the 3D geometry and 2D texture maps, depicting the saliency of the textured model, distortion of the texture mapping, and boundary of the texture atlas. These visually important areas are expressed as a visual importance map. According to the particularity of the texture map, a hybrid ROI coding method that utilizes Max-Shift and an improved post compression rate distortion (PCRD) technique is presented, guided by this visual importance map. To find the exact wavelet coefficients pertaining to these ROIs before carrying out the hybrid ROI coding, this paper proposes a stochastic coefficient priority mask map computational method. Experimental results show that the visually important areas of the texture image have a better visual effect and that a good rendering result can be obtained from the texture mapping.

Four dimensional image is 3D volume data that varies with time. It is used to express deforming or moving object in virtual surgery of 4D ultrasound. It is difficult to render 4D image by conventional ray-casting or shear-warp factorization methods because of their time-consuming rendering time or pre-processing stage whenever the volume data are changed. Even 3D texture mapping is used, repeated volume loading is also time-consuming in 4D image rendering. In this study, we propose a method to reduce data loading time using coherence between currently loaded volume and previously loaded volume in order to achieve real time rendering based on 3D texture mapping. Volume data are divided into small bricks and each brick being loaded is tested for similarity to one which was already loaded in memory. If the brick passed the test, it is defined as 3D texture by OpenGL functions. Later, the texture slices of the brick are mapped into polygons and blended by OpenGL blending functions. All bricks undergo this test. Continuously deforming fifty volumes are rendered in interactive time with SGI ONYX. Real-time volume rendering based on 3D texture mapping is currently available on PC.

Historical documents often undergo various changes over time, that alter their original state and reduce their legibility. Digital techniques are widely applied for document preservation, archiving, analysis and dissemination over the Internet. The goal of restoration is to improve the document legibility for both human and automatic operators, to extract patterns and enhance colour reproduction. Our paper presents a framework for virtual restoration of ancient documents based on a combination of multispectral acquisition, 3D imaging and digital image analysis. The proposed framework consists of several steps. First, digital representations of the documents are acquired as multispectral images and 3D surface maps, the latter reconstructed by a structured light technique. A multispectral camera and a digital projector are used in triangular configuration for 2D and 3D data acquisition. Then the multispectral images are registered against possible misalignments, and the 3D surface representation is used to correct geometrical distortions. Document flattening is then performed by 3D surface parameterization and texture mapping. Statistical techniques of decorrelation are applied to extract individual context parts of the document patterns (stamp, text, etc.) and to attenuate interferences. The processed data are then binarized by the proper segmentation technique. The entire digital object history all the acquisition and processing steps, with the corresponding parameters is stored in metadata files. These data can be exploited in a future evaluation of the restoration process and can be used for either the creation of an expert knowledge database or the extraction of cross-document observations and conclusions.

Efficient 3D face reconstruction is very important for face animation and recognition. The slow speed of the 3D morphable model is due to the texture mapping. To improve the speed, we only use the shape matching to recover the 3D shape and use texture mapping to get the texture. However, only with the shape information, one image is not enough for accurate 3D face reconstruction. So, we propose to use multiple images with the morphable shape model. First, with the feature points given on the multiple images, the 3D coordinates of the feature points are estimate by the pose estimation. Then, frontal and profile 2D morphable shape models are built to estimate the 3D morphable shape model. These two steps works iteratively to improve the result. At last, the texture is extracted from multiple images with the pose estimation from the estimated 3D face. The effectiveness of our method is demonstrated by the experimental results.

In order to better display and protect ancient Chinese architecture, a three-dimensional model reconstruction method based on multi-station laser scanning is proposed. This method mainly includes several steps, such as point cloud data collection, preconditioning, multi-site cloud data fusion, point cloud data compression, 3D model reconstruction and texture mapping, environment rendering, video processing, and 3D roaming. According to the requirement of video rendering and virtual roaming, we focus on cloud processing, 3D modeling and 3D model display in this paper. Experimental results show that an famous building named Enshi Dong Drum Tower is well digitally reconstructed, so as to result in ethnic characteristics and cultural heritage protection in practical application.

Given the technical requirements for equipment storage in the power industry, conventional storage methods prove inadequate for managing specialized materials such as precision instruments. To address texture distortion and detail loss in 3D visualization of such equipment, this study establishes a fused rendering algorithm integrating Dynamic Weighted Linear Interpolation (DWLI) and Adaptive Texture Mapping (ATM). The innovative contributions are threefold in several aspects. Firstly, we propose a Triple-Feature Descriptor (TFD) that categorizes surface characteristics across three orthogonal dimensions: geometric structure, material properties, and photometric attributes. This approach enhances feature discriminability by 32.7% compared to conventional methods. Secondly, our curvature-adaptive sampling strategy dynamically adjusts resolution (scalable from 256 × 256 to 1024 × 1024), improving edge fidelity in precision components (e.g., miniature relays) by 19.3 dB PSNR. Thirdly, the designed mapping architecture maintains color accuracy below ΔE < 3.2 across illuminance levels of 50-1000lx. Validation on the MDPI power warehouse dataset demonstrates 91.4% material identification accuracy with real-time rendering at 28 fps (RTX 3060). Deployment at a State Grid hub warehouse elevated sorting throughput by 40% and slashed manual verification workload by 65%. Comparative evaluations against conventional Texture Mapping methods reveal performance improvements exceeding 10% in both algorithm precision and recall rates. These advancements contribute substantially to operational efficiency in warehouse management systems, particularly facilitating cross-temporal domain material allocation optimization and resource coordination. The research outcomes provide practical solutions for addressing technical challenges in modern power industry logistics management.

Maximizing visual effect is a major problem in real-time animation. A real-time hair animation framework was proposed previously by C. K. Koh and Z. Huang (2000, 2001) based on 2D representation and texture mapping. One problem is that it lacks of the volumetric effect due to its 2D nature. This paper presents a technique using the U-shape strip to solve the problem.

This paper describes a method of producing scenes for TV programs, using “dynamic 3D human models.” Dynamic 3D human models are 3D models generated from images shot by multiple cameras surrounding an actor for each frame using 3D-reconstruction and texture-mapping techniques. They can provide highly realistic images as well as natural motions without having to use a motion-capture system. In addition, they allow production to be more flexible, enabling the positions of models to be changed or multiplying the amount used. Dynamic 3D human models are therefore suitable for producing crowd scenes. Although techniques of 3D reconstruction and texture mapping have been discussed and several applications have been proposed, they have not been widely introduced into TV or movie production, because of the huge amounts of data and insufficient textural quality. By establishing an efficient production flow with recent powerful computers and 24 HD cameras, the authors succeeded in producing crowd scenes with sufficient quality for a TV program, which will be aired in December 2009. The scenes involving 1,000 soldiers can be produced by shooting several sequences with two actors. The production flow that was established is described as well as scenes that were produced using dynamic 3D human models for a drama.

This paper describes a method of producing scenes for TV program, using “dynamic 3D models”. Dynamic 3D models are 3D models generated from images shot by multiple cameras surrounding an actor for each frame using 3D-reconstruction and texture-mapping techniques. They can provide highly realistic images as well as natural motion without using a motion-capture system. In addition, they allow flexible production, so the positions of the models can be changed and the models can be duplicated. Dynamic 3D models are therefore suitable for producing crowd scenes with numerous people. Although techniques of 3D reconstruction and texture mapping have been discussed and several applications have been proposed, they have not been widely used into TV or movie production because of the size of data and insufficient textural quality. By establishing an efficient production flow with recent powerful processors, we succeeded in producing scenes with sufficient quality for a TV program, which was aired in December, 2009. The scenes involving one thousand soldiers could be produced by shooting several sequences with only two actors. We describe the production flow that we established and present some scenes that we produced using dynamic 3D models for the drama.

Fast and realistic rendering of textures, characterised by a pronounced geometry, such as for example wickerwork, rattan or beach pebbles, is still a difficult and challenging problem in computer graphics. These effects can neither be simulated with 2D texture mapping nor with bump mapping. Direct geometric models or “volumetric” texturing approaches often become inevitable. All of them, however, imply excessive computational requirements. In this paper, the concept of bi-directional texture function (BTF) is introduced. A BTF permits a realistic simulation of the above mentioned effects at very low computational cost. Principles generally applied at microscale in the case of BRDFs are transposed at larger geometric scale. This allows us a direct generalisation of texture mapping and leads to many visual simulations beyond the possibilities of usual “fast” texturing techniques.

A vision–based 3‐D scene analysis system is described that is capable to model complex real–world scenes like streets and buildings automatically from stereoscopic image pairs. Input to the system is a sequence of stereoscopic images taken with two standard CCD Cameras and TV lenses. The relative orientation of both cameras to each other is known by calibration. The camerapair is then moved throughout the scene and a long sequence of closely spaced views is recorded. Each of the stereoscopic image pairs is rectified and a dense map of 3‐D suface points is obtained by area correlation, object segmentation, interpolation, and triangulation. 3‐D camera motion relative to the scene coordinate system is tracked directly from the image sequence which allows to fuse 3‐D surface measurements from different viewpoints into a consistent 3‐D model scene. The surface geometry of each scene object is approximated by a triangular surface mesh which stores the suface texture in a texture map. From the textured 3‐D models, realistic looking image sequences from arbitrary view points can be synthesized using computer graphics.

A vision-based 3-D scene analysis system is described that is capable to model complex real-world scenes like buildings automatically from stereoscopic image pairs. Input to the system is a sequence of stereoscopic images taken with two standard CCD Cameras and TV lenses. The relative orientation of both cameras to each other is estimated by calibration. The camera pair is then moved throughout the scene and a long sequence of closely spaced views is recorded. Each of the stereoscopic image pairs is rectified and a dense map of 3-D surface points is obtained by area correlation, object segmentation, interpolation, and triangulation. 3-D camera motion relative to the scene coordinate system is tracked directly from the image sequence which allows to fuse 3-D surface measurements from different view points into a consistent 3-D scene model. The surface geometry of each scene object is approximated by a triangular surface mesh which stores the surface texture in a texture map. From the textured 3-D models, realistic looking image sequences from arbitrary view points can be synthesized using computer graphics.

Image based modeling and rendering techniques have become increasingly popular for creating and visualizing 3D models from a set of images. Typically, these techniques depend on view-dependent texture mapping to render the textured 3D models in which the texture of novel views is synthesized at runtime according to different view-points. This is computationally expensive and limits their application in domains where efficient computations are required, such as games and virtual reality. In this paper we present an offline technique for creating view-independent texture atlases for 3D models, given a set of registered images. The best texture map resolution is computed by considering the areas of the projected polygons in the images. Texture maps are generated by a weighted composition of all available image information in the scene.Assuming that all surfaces of the model are exhibiting Lambertian reflectance properties, ray-tracing is then employed, for creating the view-independent texture maps. Finally, all the generated texture maps are packed into texture atlases. The result is a 3D model with an associated view-independent texture atlas which can be used efficiently in any application without any knowledge of camera pose information.

Splatting is widely applied in many areas, including volume, point-based and image-based rendering. Improvements to splatting, such as eliminating popping and color bleeding, occasion-based acceleration, post-rendering classification and shading, have all been recently accomplished. These improvements share a common need for efficient frame-buffer accesses. We present an optimized software splatting package, using a newly designed primitive, called FastSplat, to scan-convert footprints. Our approach does not use texture mapping hardware, but supports the whole pipeline in memory. In such an integrated pipeline, we are then able to study the optimization strategies and address image quality issues. While this research is meant for a study of the inherent trade-off of splatting, our renderer, purely in software, achieves 3- to 5-fold speedups over a top-end texture hardware implementation (for opaque data sets). We further propose a method of efficient occlusion culling using a summed area table of opacity. 3D solid texturing and bump mapping capabilities are demonstrated to show the flexibility of such an integrated rendering pipeline. A detailed numerical error analysis, in addition to the performance and storage issues, is also presented. Our approach requires low storage and uses simple operations. Thus, it is easily implementable in hardware.

An attempt to use CC technology to bring to life the art of Chinese ink brush painting. It has the usual elements found in Chinese paintings like the lotus, koi, lady, rock, tree and calligraphy. All the objects are 3D geometry with the unique Chinese brush strokes realized through a combination of models and shaders. Texture maps have been kept to a minimum while using simple lighting. Copyright held by creator.