Martin Bertram

Biorthogonal loop-subdivision wavelets

We present a biorthogonal wavelet construction for Loop subdivision, based on the lifting scheme. Our wavelet transform uses scaling functions that are recursively defined by Loop subdivision for arbitrary manifold triangle meshes. We orthogonalize our wavelets with respect to local scaling functions. This way, the wavelet analysis computes locally a least squares fit when reducing the resolution and converting geometric detail into sparse wavelet coefficients. The contribution of our approach is local computation of both, wavelet analysis and synthesis in linear time. We provide numerical examples supporting the stability of our scheme.

Generalized B-spline subdivision-surface wavelets for geometry compression

We present a new construction of lifted biorthogonal wavelets on surfaces of arbitrary two-manifold topology for compression and multiresolution representation. Our method combines three approaches: subdivision surfaces of arbitrary topology, B-spline wavelets, and the lifting scheme for biorthogonal wavelet construction. The simple building blocks of our wavelet transform are local lifting operations performed on polygonal meshes with subdivision hierarchy. Starting with a coarse, irregular polyhedral base mesh, our transform creates a subdivision hierarchy of meshes converging to a smooth limit surface. At every subdivision level, geometric detail is expanded from wavelet coefficients and added to the surface. We present wavelet constructions for bilinear, bicubic, and biquintic B-spline subdivision. While the bilinear and bicubic constructions perform well in numerical experiments, the biquintic construction turns out to be unstable. For lossless compression, our transform is computed in integer arithmetic, mapping integer coordinates of control points to integer wavelet coefficients. Our approach provides a highly efficient and progressive representation for complex geometries of arbitrary topology.

Phonon tracing for auralization and visualization of sound

We present a new particle tracing approach for the simulation of mid- and high-frequency sound. Inspired by the photorealism obtained by methods like photon mapping, we develop a similar method for the physical simulation of sound within rooms. For given source and listener positions, our method computes a finite-response filter accounting for the different reflections at various surfaces with frequency-dependent absorption coefficients. Convoluting this filter with an anechoic input signal reproduces a realistic aural impression of the simulated room. We do not consider diffraction effects due to low frequencies, since these can be better computed by finite elements. Our method allows the visualization of a wave front propagation using color-coded blobs traversing the paths of individual phonons.

Moment Invariants for the Analysis of 2D Flow Fields

We present a novel approach for analyzing two-dimensional (2D) flow field data based on the idea of invariant moments. Moment invariants have traditionally been used in computer vision applications, and we have adapted them for the purpose of interactive exploration of flow field data. The new class of moment invariants we have developed allows us to extract and visualize 2D flow patterns, invariant under translation, scaling, and rotation. With our approach one can study arbitrary flow patterns by searching a given 2D flow data set for any type of pattern as specified by a user. Further, our approach supports the computation of moments at multiple scales, facilitating fast pattern extraction and recognition. This can be done for critical point classification, but also for patterns with greater complexity. This multi-scale moment representation is also valuable for the comparative visualization of flow field data. The specific novel contributions of the work presented are the mathematical derivation of the new class of moment invariants, their analysis regarding critical point features, the efficient computation of a novel feature space representation, and based upon this the development of a fast pattern recognition algorithm for complex flow structures.

Comparative Visualization for Wave-based and Geometric Acoustics

We present a comparative visualization of the acoustic simulation results obtained by two different approaches that were combined into a single simulation algorithm. The first method solves the wave equation on a volume grid based on finite elements. The second method, phonon tracing, is a geometric approach that we have previously developed for interactive simulation, visualization and modeling of room acoustics. Geometric approaches of this kind are more efficient than FEM in the high and medium frequency range. For low frequencies they fail to represent diffraction, which on the other hand can be simulated properly by means of FEM. When combining both methods we need to calibrate them properly and estimate in which frequency range they provide comparable results. For this purpose we use an acoustic metric called gain and display the resulting error. Furthermore we visualize interference patterns, since these depend not only on diffraction, but also exhibit phase-dependent amplification and neutralization effects

Multiresolution distance volumes for progressive surface compression

We present a surface compression method that stores surfaces as wavelet-compressed signed-distance volumes. Our approach enables the representation of surfaces with complex topology and arbitrary numbers of components within a single multiresolution data structure. This data structure elegantly handles topological modification at high compression rates. Our method does not require the costly and sometimes infeasible base mesh construction step required by subdivision surface approaches. We present several improvements over previous attempts at compressing signed-distance functions, including an O(n) distance transform, a zero set initialization method for triangle meshes, and a specialized thresholding algorithm. We demonstrate the potential of sampled distance volumes for surface compression and progressive reconstruction for complex high genus surfaces.

Non-manifold mesh extraction from time-varying segmented volumes used for modeling a human heart

We present a new algorithm extracting and fairing surfaces from segmented volumes composed of multiple materials. In a first pass, the material boundaries in the volume are smoothed considering signed distance functions for the individual materials. Second, we apply a marching-cubes-like contouring method providing initial meshes defining material boundaries. Non-manifold features emerge along lines where more than two materials encounter. Finally, the mesh geometry is relaxed in a constrained fairing process. We use our algorithm to construct a heart model from segmented time-varying magnetic resonance images. Information concerning the heart ontology is used to merge certain structures to functional units.

Piecewise optimal triangulation for the approximation of scattered data in the plane

Abstract We present an efficient algorithm to obtain a triangulated graph surface for scattered points (x i y i ) T , i=1,…,n, with associated function values fi. The maximal distance between the triangulated graph surface and the function values is measured in z-direction (z=f(x,y)) and lies within a user-defined tolerance. The number of triangles is minimized locally by adapting their shapes to different second-degree least squares approximations of the underlying data. The method consists of three major steps: 1. subdividing the given discrete data set into clusters such that each cluster can be approximated by a quadratic polynomial within a prescribed tolerance; 2. optimally triangulating the graph surface of each quadratic polynomial; and 3. “stitching” the triangulations of all graph surfaces together. We also discuss modifications of the algorithm that are necessary to deal with discrete data points, without connectivity information, originating from a general two-manifold surface, i.e., a surface in three-dimensional space that is not necessarily a graph surface.

Visualizing the phonon map

In this work we present several visualization approaches for analyzing acoustic behavior inside a room. Our methods are based on the results of the phonon tracing algorithm. For a simulated phonon map we examine the influence of the room surfaces on the wave fronts during their propagation from the sound source. Our visualization is based on individual phonon and surface representations as well as scattered data interpolation. Additionally, an observation of acoustic behavior at different positions inside the room using colored and deformed spheres is possible.

Wavelet representation of contour sets

We present a new wavelet compression and multiresolution modeling approach for sets of contours (level sets). In contrast to previous wavelet schemes, our algorithm creates a parametrization of a scalar field induced by its contours and compactly stores this parametrization rather than function values sampled on a regular grid. Our representation is based on hierarchical polygon meshes with subdivision connectivity whose vertices are transformed into wavelet coefficients. From this sparse set of coefficients, every set of contours can be efficiently reconstructed at multiple levels of resolution. When applying lossy compression, introducing high quantization errors, our method preserves contour topology, in contrast to compression methods applied to the corresponding field function. We provide numerical results for scalar fields defined on planar domains. Our approach generalizes to volumetric domains, time-varying contours, and level sets of vector fields.