VVG: Vision, Video, and Graphics

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/1028

Browse

Now showing 1 - 20 of 67

3D Image Analysis and Synthesis at MPI Informatik
(The Eurographics Association, 2005) Theobalt, Christian; Magnor, Marcus A.; Seidel, Hans-Peter; Mike Chantler
In the talk, we give a brief overview of the research done in the Computer Graphics Group and the Graphics- Optics-Vision Group of the Max-Planck-Institut für Informatik in the area of 3D Image Analysis and Synthesis. In this context, we address the whole pipeline ranging from the acquisition of computational scene models, over the algorithmic processing of these scene descriptions, to their photo-realistic rendition in the computer. This paper illustrates the questions that we are trying to answer by means of one of our research projects, video-based rendering. We have developed a model-based system to acquire, reconstruct and render free-viewpoint videos of human actors that nicely illustrates the concept of 3D Image Analysis and Synthesis.
3D S.O.M.- A Commercial Software Solution to 3D Scanning
(The Eurographics Association, 2003) Baumberg, A.; Lyons, A.; Taylor, R.; Peter Hall and Philip Willis
This paper describes the novel features of a commercial software-only solution to 3D scanning - the 3D Software Object Modeller (3D S.O.M.). Our work is motivated by the desire to produce a low-cost, portable 3D scanning system based on hand-held digital photographs. We describe the novel techniques we have employed to achieve a robust software-based system in the areas of camera calibration, surface generation and texture extraction.
Adaptive Grid Optical Tomography
(The Eurographics Association, 2005) Ihrke, Ivo; Magnor, Marcus; Mike Chantler
Image-based modeling of semi-transparent, dynamic phenomena is a challenging task. We present an optical tomography method that uses an adaptive grid for the reconstruction of a three-dimensional density function from its projections. The proposed method is applied to reconstruct thin smoke and flames volumetrically from synchronized multi-video recordings. Our adaptive reconstruction algorithm computes a time-varying volumetric model, that enables the photorealistical rendering of the recorded phenomena from arbitrary viewpoints. In contrast to previous approaches we sample the underlying unknown, three-dimensional density function adaptively which enables us to achieve a higher effective resolution of the reconstructed models.
Advances in Shadow Removing for Motion Detection Algorithms
(The Eurographics Association, 2005) Spagnolo, P.; D'Orazio, T.; Leo, M.; Distante, A.; Mike Chantler
Detecting moving objects is very important in many application contexts such as people detection and recognition, visual surveillance, automatic generation of video effects, and so on. Motion detection algorithms are very sensible to light conditions; in particular they suffer the presence of shadows and sudden changes due to light switches. Here we propose an additional module that can be applied to a generic gray-level motion detection algorithm. The only requirement is the presence of a reference image (background model). The main idea of the proposed approach is that variations in light conditions alter the intensity values of pixels in the image, but the basic structures in the scene remain unchanged. The algorithm we propose is based on the correlation between regions selected from the reference image and the current one. The experiments have been performed on image sequences acquired both in indoor and outdoor environments with natural and artificial lights.
Applications of Clifford Algebra in Mixed Reality Environment
(The Eurographics Association, 2003) Ho, E.Y.T.; Peter Hall and Philip Willis
The 'beauty' of Clifford's Geometric Algebras is its ability to incorporate other algebras and it is the 'mother' algebra for all algebras. This paper introduces the advantage of using this algebra by combining and augmenting certain group of algebras, such as linear algebra, quaternion algebra, the Grassmann algebra and projective algebra to simplify mathematical manipulations in 3-dimensional rotations and projective geometry, especially in the context of mixed reality environment. Those 'augmented' representations are shown with applications in the mixed reality environment, especially for registration and computer vision based object recognition issues. Some simple scenarios with place-holder objects are described at the end for a full understanding of the mixed reality applications before other most recent engineering and computer science areas using this algebra for their applications are briefly discussed.
Automatic Non-Photorealistic Rendering through Soft-Shading Removal: A Colour-Vision Approach
(The Eurographics Association, 2005) Olmos, A.; Kingdom, F. A. A.; Mike Chantler
This paper presents a non-photorealistic rendering algorithm that produces "stylised-style" images by removing the soft shading from the image and by giving objects extra definition through black outlines. The method of shading removal is based on a model of the architecture of the human colour vision system. Some image results are provided and the possible extension of the algorithm using a back-propagation neural network is discussed.
Bitvectors for Robust Hierarchical Template Matching
(The Eurographics Association, 2005) Tweed, David; Mike Chantler
Many target detection problems involve objects where the primary variability in appearance is due to changes amongst characteristic configurations (as opposed to the systematic variability of object rotation or illumination changes). It is then important to utilise as much of the correlation between features as possible. Detecting pedestrians is such a problem and was tackled by Gavrila [Gav98] using a large set of exemplar templates combined with hierarchical matching via Distance Transforms. We describe a variant using a robust distance function and explicit allowance for occlusions. Our innovation is using bitwise logical operators to test against multiple exemplars in parallel.
Cartoon-Style Rendering of Motion from Video
(The Eurographics Association, 2003) Collomosse, J.P.; Hall, P.M.; Peter Hall and Philip Willis
The contribution of this paper is a novel non-photorealistic rendering (NPR) system capable of rendering motion within a video sequence in artistic styles. A variety of cartoon-style motion cues may be inserted into a video sequence, including augmentation cues (such as streak lines, ghosting, or blurring) and deformation cues (such as squash and stretch or drag effects). Users may select from the gamut of available styles by setting parameters which in uence the placement and appearance of motion cues. Our system draws upon techniques from both the vision and the graphics communities to analyse and render motion and is entirely automatic, aside from minimal user interaction to bootstrap a feature tracker. We demonstrate successful application of our system to a variety of subjects with complexities ranging from simple oscillatory to articulated motion, under both static and moving camera conditions with occlusion present. We conclude with a critical appraisal of the system and discuss directions for future work.
Coding 3D Facial Models forMugshot Applications
(The Eurographics Association, 2003) Hyde, J.; Robinson, J.; Peter Hall and Philip Willis
Three-dimensional information about a human face may have some correlation with the colour information present in its flat texture image. In order to maximise the available information for human identification of faces, a variety of coding schemes based on Binary Tree Predictive Coding 5 (BTPC5) are proposed and evaluated against similar schemes applied to the JPEG coder. The results of these schemes are presented quantatively with some discussion of the subjective results.
Collaborative Vision and Interactive Mosaicing
(The Eurographics Association, 2003) Robinson, J.A.; Peter Hall and Philip Willis
I propose criteria for collaborative vision applications where a camera user/operator and a computer work together to analyse a scene. An example of how these may be fulfilled is provided in IMP - an interactive mosaicing program.IMP generates mosaics in real-time, interacting with the user to cue camera movement and relay performance in-formation.
Color Reduction by Using a new Self-Growing and Self-Organized Neural Network
(The Eurographics Association, 2005) Atsalakis, A.; Papamarkos, N.; Mike Chantler
A new method for the reduction of the number of colors in a digital image is proposed. The new method is based on the developed of a new neural network classifier that combines the advantages of the Growing Neural Gas (GNG) and the Kohonen Self-Organized Feature Map (SOFM) neural networks. We call the new neural network: Self-Growing and Self- Organized Neural Gas (SGONG). Its main advantage is that it defines the number of the created neurons and their topology in an automatic way. As a consecutive, isolated color classes, which may correspond to significant image details, can be obtained. The SGONG is fed by the color components and additional spatial features. To speed up the entire algorithm and to reduce memory requirements, a fractal scanning sub-sampling technique is used. The method is applicable to any type of color images and it can accommodate any type of color space.
Correspondenceless Stereo for 3-D Iris Location
(The Eurographics Association, 2005) Anderson, Tom; Trucco, Emanuele; Razeto, Marco; Mike Chantler
We present a correspondenceless stereo system locating the circular contour of an iris (limbus) in space, and therefore its 3-D plane. We avoid correspondence search completely by intersecting a bundle of conjugate epipolar lines with the elliptical images of the limbus in the stereo pair of images, which gives correspondences directly. The ellipses are located by active ellipse fitting. An efficient simulated annealing implementation achieves reliable iris location with uncontrolled illumination and eye or head movements. Tests with ground-truthed 3-D setups as well as real eye images indicate very good accuracy.
Depth Enhanced Panoramas
(The Eurographics Association, 2005) Bahmutov, Gleb; Popescu, Voicu; Mudure, Mihai; Sacks, Elisha; Mike Chantler
Depth enhanced panoramas are a practical solution to the difficult problem of inside-looking-out modeling. Depth enhanced panoramas extend color panoramas to support viewpoint translation, while retaining their speed, convenience, and low cost. Depth enhanced panoramas are built incrementally from same-center-of-projection dense-color and sparse-depth frames that are acquired, registered, and merged at the rate of 5 frames per second. The evolving depth enhanced panorama is rendered continually to provide immediate operator feedback. The viewpoint translation range is increased by combining multiple depth enhanced panoramas in real time. Depth enhanced panoramas are combined using either a splat-based, disconnected representation, or, at pixel level, using a GPU fragment program. Depth enhanced panoramas are built in minutes with $3,000 hardware and support photorealistic rendering of complex room-sized environments.
Different Medical Modelling Strategies in a Single Collaborative Immersive Virtual Environment
(The Eurographics Association, 2005) Al-khalifah, A.; McCrindle, R.; Alexandrov, V.; Mike Chantler
Visualisation and simulation systems are becoming increasingly popular nowadays in medical planning and training. These tools are built using various technologies, such as computer graphics, Virtual Reality, and three dimensional (3D) modelling. The latter is an important element to these systems, because it governs how models are represented and how they can be manipulated. In this paper, we investigate the use of various 3D modelling techniques in a virtual immersive collaborative environment. We highlight the merits and limitations of these techniques, explain how they can be used in a virtual medical context, and demonstrate a practical application.
Digitisation to Presentation- BuildingVirtual Museum Exhibitions
(The Eurographics Association, 2003) Patel, M.; White, M.; Walczak, K.; Sayd, P.; Peter Hall and Philip Willis
We describe an innovative system designed for museums to create, manage and present multimedia based representations of museum artefacts in virtual exhibitions both inside and outside museums. Our system creates digital surrogates through a novel stereo photogrammetry system with little user interaction. The resulting 3D objects are refined using state-of-the-art 3D modelling software configured for ease of use by museum staff. A repository of such digital surrogates is managed in an XML enabled relational database and provides the basis for the creation and presentation of virtual museum exhibitions, allowing current museum websites to evolve from a 2D to a 3D multimedia-rich domain. In this paper, we discuss the modelling and refinement processes which are based on stereo photogrammetry and the creation and visualisation of virtual museum exhibitions using virtual and augmented reality techniques.
Efficient 3D Content Creation using Point Sampled Geometry
(The Eurographics Association, 2003) Gross, Markus; Peter Hall and Philip Willis
In recent years, point primitives have received a growing attention in computer graphics. The emergence of affordable 3D scanning devices along with the demand for ever more geometric detail has created the need to efficiently process and display very large point sampled models. At data sizes where triangle based methods approach their limits, point representations feature a variety of advantages. Since points provide a discretization of geometry without explicit storage of topology, they enable us to generate highly optimized object representations. In spite of the great challenges they pose for graphics processing, the latest generation of algorithms includes advanced modeling, sophisticated geometry processing, and high quality rendering. In this talk I will introduce points as a powerful and versatile graphics primitive for efficient 3D content creation and present a survey the latest research results in point based computer graphics. Novel concepts for the representation of point sampled shapes will be discussed, as well as algorithms for interactive modeling of point clouds. In addition, I will address methods for geometric processing, filtering and resampling of point models. I will also give examples of algorithms for high performance rendering of point clouds, including advanced shading, antialiasing, and transparency. Finally, I will introduce Pointshop3D, an open source software for 3D photo editing of point sampled geometry, which includes all of the presented algorithms.
An Eigenvector Method for Surface Recovery
(The Eurographics Association, 2003) Robles-Kelly, A.; Hancock, E.R.; Peter Hall and Philip Willis
In this paper we explore how spectral methods for graph seriation can be used to develop a new shape-fromshading algorithm. We characterise the field of surface normals using a transition matrix whose elements are computed from the sectional curvature between different image locations. We use a graph seriation method to define a curvature minimising surface integration path for the purposes of height reconstruction. To smooth the reconstructed surface, we fit quadric patches to the height data. The smoothed surface normal directions are updated ensuring compliance with Lambert's law. The processes of height recovery and surface normal adjustment are interleaved and iterated until a stable surface is obtained. We provide results on synthetic and real-world imagery.
Enhanced Texture Editing using Self Similarity
(The Eurographics Association, 2003) Brooks, S.; Cardle, M.; Dodgson, N.A.; Peter Hall and Philip Willis
Texture mapping is an indispensable tool for achieving realism in computer graphics. Significant progress has been made in recent years with regards to the synthesis and editing of 2D texture images. However, the exploration of user control for semi-automatic texture editing remains an open area of research. We present methods that partially address the semantic and technical limitations of Self-Similarity Based Editing. This is achieved by providing the user with more control over the similarity metric during editing and over spatial rearrangement during cloning.
Extending Natural Textures with Multi-Scale Synthesis
(The Eurographics Association, 2003) Stahlhut, O.; Peter Hall and Philip Willis
This paper presents a texture synthesis algorithm that was designed for the tile-less generation of large images of arbitrary size from small sample images. The synthesised texture shows features that are visually similar to the sample over a wide frequency range. The development of the algorithm aimed at achieving high quality results for a large range of natural textures, incorporation of the original samples in the synthesis product, ease of use and good texturing speed even with input sample data two magnitudes larger than used by previous techniques. Like other algorithms we utilise an implicit texture model by copying arbitrary shaped texture patches from the sample to the destination over a multi-scale image pyramid. Our method combines the advantages of different previous techniques with respect to quality. A mixture of exhaustive searching, massive parallel computing and the well-known LBG-algorithm ensures a good balance between texturing quality and speed.
A Flexible and Versatile Studio for Synchronized Multi-View Video Recording
(The Eurographics Association, 2003) Theobalt, C.; Li, M.; Magnor, M.A.; Seidel, H.-P.; Peter Hall and Philip Willis
In recent years, the convergence of computer vision and computer graphics has put forth new research areas that work on scene reconstruction from and analysis of multi-view video footage. In free-viewpoint video, for example, new views of a scene are generated from an arbitrary viewpoint in real-time using a set of multi-view video streams as inputs. The analysis of real-world scenes from multi-view video to extract motion information or reflection models is another field of research that greatly benefits from high-quality input data. Building a recording setup for multi-view video involves a great effort on the hardware as well as the software side. The amount of image data to be processed is huge, a decent lighting and camera setup is essential for a naturalistic scene appearance and robust background subtraction, and the computing infrastructure has to enable real-time processing of the recorded material. This paper describes our recording setup for multi-view video acquisition that enables the synchronized recording of dynamic scenes from multiple camera positions under controlled conditions. The requirements to the room and their implementation in the separate components of the studio are described in detail. The efficiency and flexibility of the room is demonstrated on the basis of the results that we obtain with a real-time 3D scene reconstruction system, a system for non-intrusive optical motion capture and a model-based free-viewpoint video system for human actors.

Browse

Browsing VVG: Vision, Video, and Graphics by Title

Results Per Page

Sort Options