Browsing by Author "Reinbold, Christian"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Learning Generic Local Shape Properties for Adaptive Super-Sampling
    (The Eurographics Association, 2022) Reinbold, Christian; Westermann, Rüdiger; Pelechano, Nuria; Vanderhaeghe, David
    We propose a novel encoder/decoder-based neural network architecture that learns view-dependent shape and appearance of geometry represented by voxel representations. Since the network is trained on local geometry patches, it generalizes to arbitrary models. A geometry model is first encoded into a sparse voxel octree of features learned by a network, and this model representation can then be decoded by another network in-turn for the intended task. We utilize the network for adaptive supersampling in ray-tracing, to predict super-sampling patterns when seeing coarse-scale geometry. We discuss and evaluate the proposed network design, and demonstrate that the decoder network is compact and can be integrated seamlessly into on-chip ray-tracing kernels. We compare the results to previous screen-space super-sampling strategies as well as non-network-based world-space approaches.
  • Thumbnail Image
    Item
    Parameterized Splitting of Summed Volume Tables
    (The Eurographics Association and John Wiley & Sons Ltd., 2021) Reinbold, Christian; Westermann, Rüdiger; Borgo, Rita and Marai, G. Elisabeta and Landesberger, Tatiana von
    Summed Volume Tables (SVTs) allow one to compute integrals over the data values in any cubical area of a three-dimensional orthogonal grid in constant time, and they are especially interesting for building spatial search structures for sparse volumes. However, SVTs become extremely memory consuming due to the large values they need to store; for a dataset of n values an SVT requires O(nlogn) bits. The 3D Fenwick tree allows recovering the integral values in O(log3 n) time, at a memory consumption ofO(n) bits.We propose an algorithm that generates SVT representations that can flexibly trade speed for memory: From similar characteristics as SVTs, over equal memory consumption as 3D Fenwick trees at significantly lower computational complexity, to even further reduced memory consumption at the cost of raising computational complexity. For a 641x9601x9601 binary dataset, the algorithm can generate an SVT representation that requires 27.0 GB and 46 . 8 data fetch operations to retrieve an integral value, compared to 27.5 GB and 1521 . 8 fetches by 3D Fenwick trees, a decrease in fetches of 97%. A full SVT requires 247.6GB and 8 fetches per integral value. We present a novel hierarchical approach to compute and store intermediate prefix sums of SVTs, so that any prescribed memory consumption between O(n) bits and O(nlogn) bits is achieved. We evaluate the performance of the proposed algorithm in a number of examples considering large volume data, and we perform comparisons to existing alternatives.