Search Results

Now showing 1 - 10 of 49
  • 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
    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
    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
    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.
  • Item
    Isogeometric Analysis for Modelling and Design
    (The Eurographics Association, 2015) Riffnaller-Schiefer, Andreas; Augsdörfer, Ursula H.; Fellner, Dieter W.; B. Bickel and T. Ritschel
    We present an isogeometric design and analysis approach based on NURBS-compatible subdivision surfaces. The approach enables the description of watertight free-form surfaces of arbitrary degree, including conic sections and an accurate simulation and analysis based directly on the designed surface. To explore the seamless integration of design and analysis provided by the isogeometric approach, we built a prototype software which combines free-form modelling tools with thin shell simulation tools to offer the designer a wide range of design and analysis instruments.
  • Item
    Direct Limit Volumes: Constant-Time Limit Evaluation for Catmull-Clark Solids
    (The Eurographics Association, 2018) Altenhofen, Christian; Müller, Joel; Weber, Daniel; Stork, André; Fellner, Dieter W.; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present a novel approach for efficient limit volume evaluation on Catmull-Clark (CC) subdivision solids. Although several analogies exist between subdivision surfaces and subdivision volumes, extending Stam's limit evaluation technique from 2 to 3 dimensions is not straightforward, as irregularities and boundaries introduce new challenges in the volumetric case. We present new direct evaluation techniques for irregular volumetric topologies and boundary cells, which allow for calculating the limit of CC subdivision solids at arbitrary parameter values in constant time. Evaluation of limit points is a central aspect when using CC solids for applications such as simulation and multi-material additive manufacturing, or as a compact volumetric representation scheme for continuous scalar fields. We demonstrate that our approach is faster than existing evaluation techniques for every topological configuration or target parameter (u, v, w) that requires more than two local subdivision steps.
  • Item
    Fast Motion Rendering for Single-Chip Stereo DLP Projectors
    (The Eurographics Association, 2012) Lancelle, Marcel; Voß, Gerrit; Fellner, Dieter W.; Ronan Boulic and Carolina Cruz-Neira and Kiyoshi Kiyokawa and David Roberts
    Single-chip color DLP projectors show the red, green and blue components one after another. When the gaze moves relative to the displayed pixels, color fringes are perceived. In order to reduce these artefacts, many devices show the same input image twice at the double rate, i.e. a 60Hz source image is displayed with 120Hz. Consumer stereo projectors usually work with time interlaced stereo, allowing to address each of these two images individually. We use this so called 3D mode for mono image display of fast moving objects. Additionally, we generate a separate image for each individual color, taking the display time offset of each color component into account. With these 360 images per second we can strongly reduce ghosting, color fringes and jitter artefacts on fast moving objects tracked by the eye, resulting in sharp objects with smooth motion. Real-time image generation at such a high frame rate can only be achieved for simple scenes or may only be possible by severely reducing quality. We show how to modify a motion blur post processing shader to render only 60frames