Search Results

Now showing 1 - 10 of 80
  • Item
    DeepTex: Deep Learning-Based Texturing of Image-Based 3D Reconstructions
    (The Eurographics Association, 2024) Neumann, Kai Alexander; Santos, Pedro; Fellner, Dieter W.; Corsini, Massimiliano; Ferdani, Daniele; Kuijper, Arjan; Kutlu, Hasan
    Image-based 3D reconstruction is a commonly used technique for measuring the geometry and color of objects or scenes based on images. While the geometry reconstruction of state-of-the-art approaches is mostly robust against varying lighting conditions and outliers, these pose a significant challenge for calculating an accurate texture map. This work proposes a deep-learning based texturing approach called ''DeepTex'' that uses a custom learned blending method on top of a traditional mosaic-based texturing approach. The model was trained using a custom synthetic data generation workflow and showed a significantly increased accuracy when generating textures in the presence of outliers and non-uniform lighting.
  • Item
    c-Space: Time-evolving 3D Models (4D) from Heterogeneous Distributed Video Sources
    (The Eurographics Association, 2016) Ritz, Martin; Knuth, Martin; Domajnko, Matevz; Posniak, Oliver; Santos, Pedro; Fellner, Dieter W.; Chiara Eva Catalano and Livio De Luca
    We introduce c-Space, an approach to automated 4D reconstruction of dynamic real world scenes, represented as time-evolving 3D geometry streams, available to everyone. Our novel technique solves the problem of fusing all sources, asynchronously captured from multiple heterogeneous mobile devices around a dynamic scene at a real word location. To this end all captured input is broken down into a massive unordered frame set, sorting the frames along a common time axis, and finally discretizing the ordered frame set into a time-sequence of frame subsets, each subject to photogrammetric 3D reconstruction. The result is a time line of 3D models, each representing a snapshot of the scene evolution in 3D at a specific point in time. Just like a movie is a concatenation of time-discrete frames, representing the evolution of a scene in 2D, the 4D frames reconstructed by c-Space line up to form the captured and dynamically changing 3D geometry of an event over time, thus enabling the user to interact with it in the very same way as with a static 3D model. We do image analysis to automatically maximize the quality of results in the presence of challenging, heterogeneous and asynchronous input sources exhibiting a wide quality spectrum. In addition we show how this technique can be integrated as a 4D reconstruction web service module, available to mobile end-users.
  • Item
    Adaptive Ray Tracing of Subdivision Surfaces
    (Blackwell Publishers, Inc and the Eurographics Association, 2003) Müller, Kerstin; Techmann, Torsten; Fellner, Dieter W.
    Subdivision Surfaces as well as (interactive) ray tracing have become an important issue in computer graphics.But ray tracing of subdivision surfaces has received only little attention. We present a new approach for raytracing of subdivision surfaces. The algorithm uses a projection of the ray onto the surface and works mainly intwo dimensions along this projection. While proceeding from patch to patch, we examine the bounding volume oftheir borders: the lower the distance between ray and subdivision surface, the more refinement steps are adaptivelyapplied to the surface but only along the projection of the ray. The adaptive refinement of a patch is controlled bycurvature, size, its membership to the silhouette, and its potential contribution to the light transport. The algorithmis simple and mainly consists of elementary geometric computations. Hence it is fast and easy to implementwithout the need for elaborate preprocessing. The algorithm is robust in the sense that it deals with all features ofsubdivision surfaces like creases and corners.Categories and Subject Descripters (according to ACM CCS): I.3.7 [Computer Graphics]: Raytracing
  • Item
    An Error Bound for Decoupled Visibility with Application to Relighting
    (The Eurographics Association, 2011) Schwenk, Karsten; Fellner, Dieter W.; N. Avis and S. Lefebvre
    Monte Carlo estimation of direct lighting is often dominated by visibility queries. If an error is tolerable, the calculations can be sped up by using a simple scalar occlusion factor per light source to attenuate radiance, thus decoupling the expensive estimation of visibility from the comparatively cheap sampling of unshadowed radiance and BRDF. In this paper we analyze the error associated with this approximation and derive an upper bound. We demonstrate in a simple relighting application how our result can be used to reduce noise by introducing a controlled error if a reliable estimate of the visibility is already available.
  • Item
    CultLab3D - Fast and Economic 3D Mass-Digitization
    (IEEE, 2015) Santos, Pedro; Ritz, Martin; Tausch, Reimar; Schmedt, Hendrik; Rodriguez, Rafael Monroy; Fuhrmann, Constanze; Domajnko, Matevz; Knuth, Martin; Fellner, Dieter W.; Sofia Pescarin and Pedro Cano and Alfredo Grande
    CultLab3D, the world-wide first attempt at 3D mass digitization, implements a multi-modular scanning pipeline connecting individual scanners by conveyor belts and transporting cultural heritage artefacts on corresponding trays.
  • Item
    Towards a Voting Scheme for Calculating Light Source Positions from a given Target Illumination
    (The Eurographics Association, 2010) Zmugg, René; Havemann, Sven; Fellner, Dieter W.; Enrico Puppo and Andrea Brogni and Leila De Floriani
    Lighting conditions can make the difference between success or failure of an architectural space. The vision of space-light co-design is that architects can control the impression of an illuminated space already at an early design stage, instead of first designing spaces and then searching for a good lighting setup. As a first step towards this vision we propose a novel method to calculate potential light source positions from a given user defined target illumination. The method is independent of the tessellation of the scene and assumes a homogeneous diffuse Lambertian material. This allows using a voting system that determines potential positions for standard light sources with chosen size and brightness. Votes are cast from an illuminated surface point to all potential positions of a light source that would yield this illumination. Vote clusters consequently indicate a more probable light source position. With a slight extension the method can also identify mid-air light source positions.
  • Item
    A Cut-Cell Geometric Multigrid Poisson Solver for Fluid Simulation
    (The Eurographics Association and John Wiley & Sons Ltd., 2015) Weber, Daniel; Mueller-Roemer, Johannes; Stork, André; Fellner, Dieter W.; Olga Sorkine-Hornung and Michael Wimmer
    We present a novel multigrid scheme based on a cut-cell formulation on regular staggered grids which generates compatible systems of linear equations on all levels of the multigrid hierarchy. This geometrically motivated formulation is derived from a finite volume approach and exhibits an improved rate of convergence compared to previous methods. Existing fluid solvers with voxelized domains can directly benefit from this approach by only modifying the representation of the non-fluid domain. The necessary building blocks are fully parallelizable and can therefore benefit from multi- and many-core architectures.
  • Item
    EDEN - AN EDITOR ENVIRONMENT FOR OBJECT- ORIENTED GRAPHICS EDITING
    (Eurographics Association, 1990) Fellner, Dieter W.; Kappe, F.
    Systems allowing the creation and manipulation of graphical information (so-called Graphic Editors) have become essential in various fields of applications. At the same time the typical user of such a system has changed. Not computer experts, but designers, secretaries, technicians, teachers etc. are today's typical users of computer graphics, mostly on microcomputers. Obviously it would be desirable to have a common concept of graphics editing covering many applications. The purpose of this paper is a brief survey of the EDEN project started at the IIGb in 1987: the motivation for the project, the major steps, results, current status and future work is presented here. EDEN (short for EDitor ENvironnient) is a generic concept for object-oriented graphics editing, providing device independence at the workstation and graphics output level as well as an application independent file-format for the storage and exchange between different graphics applications.
  • Item
    Publications Board Report
    (2024-04-15) Fellner, Dieter W.
  • Item
    CultLab3D - On the Verge of 3D Mass Digitization
    (The Eurographics Association, 2014) Santos, Pedro; Ritz, Martin; Tausch, Reimar; Schmedt, Hendrik; Monroy, Rafael; Stefano, Antonio De; Posniak, Oliver; Fuhrmann, Constanze; Fellner, Dieter W.; Reinhard Klein and Pedro Santos
    Acquisition of 3D geometry, texture and optical material properties of real objects still consumes a considerable amount of time, and forces humans to dedicate their full attention to this process. We propose CultLab3D, an automatic modular 3D digitization pipeline, aiming for efficient mass digitization of 3D geometry, texture, and optical material properties. CultLab3D requires minimal human intervention and reduces processing time to a fraction of today's efforts for manual digitization. The final step in our digitization workflow involves the integration of the digital object into enduring 3D Cultural Heritage Collections together with the available semantic information related to the object. In addition, a software tool facilitates virtual, location-independent analysis and publication of the virtual surrogates of the objects, and encourages collaboration between scientists all around the world. The pipeline is designed in a modular fashion and allows for further extensions to incorporate newer technologies. For instance, by switching scanning heads, it is possible to acquire coarser or more refined 3D geometry.