Search Results

Now showing 1 - 10 of 54
  • Item
    Example-based Interpolation and Synthesis of Bidirectional Texture Functions
    (The Eurographics Association and Blackwell Publishing Ltd., 2013) Ruiters, Roland; Schwartz, Christopher; Klein, Reinhard; I. Navazo, P. Poulin
    Bidirectional Texture Functions (BTF) have proven to be a well-suited representation for the reproduction of measured real-world surface appearance and provide a high degree of realism. We present an approach for designing novel materials by interpolating between several measured BTFs. For this purpose, we transfer concepts from existing texture interpolation methods to the much more complex case of material interpolation. We employ a separation of the BTF into a heightmap and a parallax compensated BTF to cope with problems induced by parallax, masking and shadowing within the material. By working only on the factorized representation of the parallax compensated BTF and the heightmap, it is possible to efficiently perform the material interpolation. By this novel method to mix existing BTFs, we are able to design plausible and realistic intermediate materials for a large range of different opaque material classes. Furthermore, it allows for the synthesis of tileable and seamless BTFs and finally even the generation of gradually changing materials following user specified material distribution maps.
  • Item
    Appearance Bending: A Perceptual Editing Paradigm for Data-Driven Material Models
    (The Eurographics Association, 2017) Mylo, Marlon; Giesel, Martin; Zaidi, Qasim; Hullin, Matthias; Klein, Reinhard; Matthias Hullin and Reinhard Klein and Thomas Schultz and Angela Yao
    Data-driven representations of material appearance play an important role in a wide range of applications. Unlike with analytical models, however, the intuitive and efficient editing of tabulated reflectance data is still an open problem. In this work, we introduce appearance bending, a set of image-based manipulation operators, such as thicken, inflate, and roughen, that implement recent insights from perceptual studies. In particular, we exploit a link between certain perceived visual properties of a material, and specific bands in its spectrum of spatial frequencies or octaves of a wavelet decomposition. The result is an editing interface that produces plausible results at interactive rates, even for drastic manipulations. We present the effectiveness of our method on a database of bidirectional texture functions (BTFs) for a variety of material samples.
  • Item
    Unsupervised Detection and Localization of Egyptian Hieroglyphs
    (The Eurographics Association, 2024) Lion, Pauline; Trunz, Elena; Klein, Reinhard; Corsini, Massimiliano; Ferdani, Daniele; Kuijper, Arjan; Kutlu, Hasan
    The extensive variability in hieroglyph forms, coupled with erosion, fading, damage, and lighting effects, makes hieroglyphic script highly complex and difficult to segment. This complexity, along with the scarcity of labeled data, poses challenges for traditional supervised learning methods. In this paper, we present a novel unsupervised approach for detecting and localizing Egyptian hieroglyphs in images. Our method employs classical computer vision algorithms to generate pseudo-labels, which are then used to train a Faster R-CNN model. Augmented by post-processing techniques, our approach achieves detection results comparable to that of previous supervised methods for hieroglyph segmentation. Evaluated on unseen backgrounds, it demonstrates significant potential for advancing research in Egyptian culture and history.
  • Item
    Towards Efficient Online Compression of Incrementally Acquired Point Clouds
    (The Eurographics Association, 2014) Golla, Tim; Schwartz, Christopher; Klein, Reinhard; Jan Bender and Arjan Kuijper and Tatiana von Landesberger and Holger Theisel and Philipp Urban
    We present a framework for the online compression of incrementally acquired point cloud data. For this, we extend an existing vector quantization-based offline point cloud compression algorithm to handle the challenges that arise from the envisioned online scenario. In particular, we learn a codebook in advance from training data and replace a computationally demanding part of the algorithm with a faster alternative. We show that the compression ratios and reconstruction quality are comparable to the offline version while the speed is sufficiently improved. Furthermore, we investigate how well codebooks that are generated from different amounts of training data generalize to larger sets of point cloud data.
  • Item
    Towards Sparse and Multiplexed Acquisition of Material BTFs
    (The Eurographics Association, 2017) Brok, Dennis den; Weinmann, Michael; Klein, Reinhard; Reinhard Klein and Holly Rushmeier
    We present preliminary results on our effort to combine sparse and illumination-multiplexed acquisition of bidirectional texture functions (BTFs) for material appearance. Both existing acquisition paradigms deal with a single specific problem: the desire to reduce either the number of images to be obtained while maintaining artifact-free renderings, or the shutter times required to capture the full dynamic range of a material's appearance. These problems have so far been solved by means of data-driven models. We demonstrate that the way these models are derived prevents combined sparse and multiplexed acquisition, and introduce a novel model that circumvents this obstruction. As a result, we achieve acquisition times on the order of minutes in comparison to the few hours required with sparse acquisition or multiplexed illumination.
  • Item
    Frontmatter: Eurographics 2018 Workshop on Material Appearance Modeling
    (The Eurographics Association, 2018) Klein, Reinhard; Rushmeier, Holly; Reinhard Klein and Holly Rushmeier
  • Item
    Data Driven Surface Reflectance from Sparse and Irregular Samples
    (The Eurographics Association and John Wiley and Sons Ltd., 2012) Ruiters, Roland; Schwartz, Christopher; Klein, Reinhard; P. Cignoni and T. Ertl
    In recent years, measuring surface reflectance has become an established method for high quality renderings. In this context, especially non-parametric representations got a lot of attention as they allow for a very accurate representation of complex reflectance behavior. However, the acquisition of this data is a challenging task especially if complex object geometry is involved. Capturing images of the object under varying illumination and view conditions results in irregular angular samplings of the reflectance function with a limited angular resolution. Classical data-driven techniques, like tensor factorization, are not well suited for such data sets as they require a resampling of the high dimensional measurement data to a regular grid. This grid has to be on a much higher angular resolution to avoid resampling artifacts which in turn would lead to data sets of enormous size. To overcome these problems we introduce a novel, compact data-driven representation of reflectance functions based on a sum of separable functions which are fitted directly to the irregular set of data without any further resampling. The representation allows for efficient rendering and is also well suited for GPU applications. By exploiting spatial coherence of the reflectance function over the object a very precise reconstruction even of specular materials becomes possible already with a sparse input sampling. This would be impossible using standard data interpolation techniques. Since our algorithm exclusively operates on the compressed representation, it is both efficient in terms of memory use and computational complexity, depending only sub-linearly on the size of the fully tabulated data. The quality of the reflectance function is evaluated on synthetic data sets as ground truth as well as on real world measurements.
  • Item
    Efficient Unsupervised Temporal Segmentation of Human Motion
    (The Eurographics Association, 2014) Vögele, Anna; Krüger, Björn; Klein, Reinhard; Vladlen Koltun and Eftychios Sifakis
    This work introduces an efficient method for fully automatic temporal segmentation of human motion sequences and similar time series. The method relies on a neighborhood graph to partition a given data sequence into distinct activities and motion primitives according to self-similar structures given in that input sequence. In particular, the fast detection of repetitions within the discovered activity segments is a crucial problem of any motion processing pipeline directed at motion analysis and synthesis. The same similarity information in the neighborhood graph is further exploited to cluster these primitives into larger entities of semantic significance. The elements subject to this classification are then used as prior for estimating the same target values for entirely unknown streams of data. The technique makes no assumptions about the motion sequences at hand and no user interaction is required for the segmentation or clustering. Tests of our techniques are conducted on the CMU and HDM05 motion capture databases demonstrating the capability of our system handling motion segmentation, clustering, motion synthesis and transfer-of-label problems in practice - the latter being an optional step which relies on the preexistence of a small set of labeled data.
  • Item
    Heightfield and spatially varying BRDF Reconstruction for Materials with Interreflections
    (The Eurographics Association and Blackwell Publishing Ltd, 2009) Ruiters, Roland; Klein, Reinhard
    Photo-realistic reproduction of material appearance from images has widespread use in applications ranging from movies over advertising to virtual prototyping. A common approach to this task is to reconstruct the small scale geometry of the sample and to capture the reflectance properties using spatially varying BRDFs. For this, multi-view and photometric stereo reconstruction can be used, both of which are limited regarding the amount of either view or light directions and suffer from either low- or high-frequency artifacts, respectively. In this paper, we propose a new algorithm combining both techniques to recover heightfields and spatially varying BRDFs while at the same time overcoming the above mentioned drawbacks. Our main contribution is a novel objective function which allows for the reconstruction of a heightfield and high quality SVBRDF including view dependent effects. Thereby, our method also avoids both low and high frequency artifacts. Additionally, our algorithm takes inter-reflections into account allowing for the reconstruction of undisturbed representations of the underlying material. In our experiments, including synthetic and real-world data, we show that our approach is superior to state-of-the-art methods regarding reconstruction error as well as visual impression. Both the reconstructed geometry and the recovered SVBRDF are highly accurate, resulting in a faithful reproduction of the materials characteristic appearance, which is of paramount importance in the context of material rendering.
  • Item
    Temporal Upsampling of Point Cloud Sequences by Optimal Transport for Plant Growth Visualization
    (© 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd, 2020) Golla, Tim; Kneiphof, Tom; Kuhlmann, Heiner; Weinmann, Michael; Klein, Reinhard; Benes, Bedrich and Hauser, Helwig
    Plant growth visualization from a series of 3D scanner measurements is a challenging task. Time intervals between successive measurements are typically too large to allow a smooth animation of the growth process. Therefore, obtaining a smooth animation of the plant growth process requires a temporal upsampling of the point cloud sequence in order to obtain approximations of the intermediate states between successive measurements. Additionally, there are suddenly arising structural changes due to the occurrence of new plant parts such as new branches or leaves. We present a novel method that addresses these challenges via semantic segmentation and the generation of a segment hierarchy per scan, the matching of the hierarchical representations of successive scans and the segment‐wise computation of optimal transport. The transport problems' solutions yield the information required for a realistic temporal upsampling, which is generated in real time. Thereby, our method does not require shape templates, good correspondences or huge databases of examples. Newly grown and decayed parts of the plant are detected as unmatched segments and are handled by identifying corresponding bifurcation points and introducing virtual segments in the previous, respectively successive time step. Our method allows the generation of realistic upsampled growth animations with moderate computational effort.