Michael Wand's Homepage

contact teaching group research publications software



Research Topics & Projects

Deep Generative Models

Generating geometry by assembling rigid pieces, as discussed above, has its limitations. It works reasonably well for man-made shapes but lacks generalization power for more complex shape families or organic data. More recently, we have therefore started looking into more complex, non-linear, distributed encodings based on deep convolutional neural networks. These techniques provide very strong invariance and remarkable flexibility in compositing different parts. Many of the key insights from the exact case studied so far carry over to this new domain.

Physical systems: We are also very interested in applying deep networks, in particular generative networks, to simulations of physical systems. This offers on the one hand a potential way for automatically building up abstractions for multi-scale simulations of complex systems but might also open up new insights on why deep learning is so effective in modeling natural patterns.

Key Publications

  • Chuan Li, Michael Wand: Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks. In: European Conference on Computer Vision (ECCV), 2016. preprint (arXiv.org)     code (github.com)
  • Chuan Li, Michael Wand: Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
    preprint (arXiv.org)     code (github.com)

Compositional Models

Our objective is to describe complex data sets by combinging a small number of building blocks using simple rules. Originally, this has been motivated by research in inverse procedural modeling (see below) methods, where 3D shapes are decomposed into topological pieces attached according to a shape grammar.

Key Publications

  • Chuan Li, Michael Wand: Approximate Translational Building Blocks for Image Decomposition and Synthesis. In: ACM Transactions on Graphics 34(5), 2015 (Presented at Siggraph 2016). paper (publisher site)
  • Chuan Li, Michael Wand, Xiaokun Wu, Hans-Peter Seidel: Approximate 3D Partial Symmetry Detection Using Co-occurrence Analysis. In: IEEE Conference on 3D Vision (3DV 2015), 2015. paper (publisher site)
  • Han Liu, Ulysse Vimont, Michael Wand, Marie-Paule Cani, Stefanie Hahmann, Damien Rohmer, and Niloy J. Mitra: Replaceable Substructures for Efficient Part-Based Modeling. In: Computer Graphics Forum 34(2) (Proc. Eurographics 2015), 2015.
    paper (PDF)     project page (link)

  • J. Kalojanov, M. Bokeloh, M. Wand, L. Guibas, H.-P. Seidel, P. Slusallek: Microtiles: Extracting Building Blocks from Correspondences, In: Computer Graphics Forum (Proc. Symposium on Geometry Processing), 2012.
    paper (PDF)

Scientific Data Analysis

We are applying our methods to the analysis of real-world data in natural science and life sciences. Our focus is on pattern recognition and both supervised and unsupervised pattern recovery. The projects are embedded in the framework of the Center for Computational Science in Mainz (CSM).

Former Projects

Inverse Procedural Modeling

Inverse procedural modeling refers to the process of estimating rules how to build a shape from one or more example shapes. We are looking at fully automatic techniques that can derive shape grammars from example shapes. We use partial symmetries of an object to find a grammar that describes a family of shapes that are similar to the exemplar in a formal sense.

Key Publications

  • M. Bokeloh, M. Wand, H.-P. Seidel: A Connection between Partial Symmetry and Inverse Procedural Modeling. In: ACM Transactions on Graphics (Siggraph 2010).
    project page, paper (high-res, 24MB), paper (low-res, 1.8MB), video (Youtube)
  • M. Bokeloh, M. Wand, V. Koltun, H.-P. Seidel: "Pattern-Aware Deformation Using Sliding Dockers", In: ACM Transactions on Graphics (Proc. Siggraph Asia), 2011.
    paper (preprint, PDF, 22MB), video (mp4, 72MB)

  • M. Bokeloh, M.Wand, H.-P. Seidel, V. Koltun: An Algebraic Model for Parameterized Shape Editing. In: Proc. SIGGRAPH 2012.
    paper (preprint, PDF, 40MB)

Symmetry Detection

Given a 3D model, we would like to compose this model into elementary building blocks. Each building block consists of the same geometry up to a certain transformation (rigid motion, isometry, more general deformation) and possibly noise. We are looking at algorithms that can compute such decompositions fully automatically, without user supervision.

Key Publications

  • M. Bokeloh, A. Berner, M.Wand, H.-P. Seidel, A. Schilling: Symmetry Detection Using Line Features. In: Computer Graphics Forum, Proc. Eurographics '09.
    paper (10 MB), video: avi/xvid (40MB) quicktime (32MB).
  • Jens Kerber, Martin Bokeloh, Michael Wand, Hans-Peter Seidel: Scalable Symmetry Detection for Urban Scenes. In: Computer Graphics Forum, 2013.
    technical report (13 MB), video (mp4, 76MB), full paper (publisher site).

Deformable Shape Matching

Our goal is to find dense correspondences between deformed shapes. We assume that the deformation the shape has undergone is intrinsically isometric, i.e., does not change geodesic distances within the deformed surface. However, we have to address the problem of topological noise (partial data, acquisition holes, apparant connections if for example the hand of a person gets to close to the body). We are looking at algorithms that can perform global isometric shape matching witout prior initialization and under topological noise. The key observation is that isometries between 2-manifolds have only very few degrees of freedom so that correspondences can be extrapolated from a small set of parameters that are easy to guess, even under noisy and partial data.

Key Publications

  • A. Tevs, A. Berner, M. Wand, I. Ihrke, H.-P. Seidel: Intrinsic Shape Matching by Planned Landmark Sampling. In: Computer Graphics Forum (Proc. Eurographics), 2011.
    project page (link), paper (20MB)
  • A. Tevs, M. Bokeloh, M.Wand, A. Schilling, H.-P. Seidel: Isometric Registration of Ambiguous and Partial Data. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '09), 2009.
    paper (2 MB), video (mp4, 30MB)
  • A. Brunton, M. Wand, Stefanie Wuhrer, Hans-Peter Seidel, Tino Weinkauf: A Low-Dimensional Representation for Robust Partial Isometric Correspondences Computation. In: Graphical Models, 2013.
    arxiv preprent (earlier version)    full paper (pubisher site)

Animation Reconstruction

We consider sequences of point clouds that shows a deformable shape in motion, as obtained from real-time 3D scanners. This means we have typically acquisition holes so that the shape is only shown partially in each frame. In addition, no correspondence information is given by the data. Our goal is to reconstruct shape and motion simultaneously, including dense correspondences over time and completed geometry in every frame that matches the data and behaves plausibly in unobserved areas. We refer to this problem setting as animation reconstruction.

Key Publications

  • A. Tevs, A. Berner, M. Wand, I. Ihrke, M. Bokeloh, J. Kerber, H.-P. Seidel: "Animation Cartography - Intrinsic Reconstruction of Shape and Motion", In: ACM Transactions on Graphics, 2012.
    project page (link), paper (10MB), video (mp4, 290MB)
  • M. Wand, B. Adams, M. Ovsjanikov, A. Berner, M. Bokeloh, P. Jenke, L. Guibas, H.-P. Seidel, A. Schilling: Efficient Reconstruction of Non-rigid Shape and Motion from Real-Time 3D Scanner Data. In: ACM Transactions on Graphics 28(2), April 2009.
    paper (8 MB), video: avi/xvid (56MB), quicktime (66MB).
  • B. Adams, M. Ovsjanikov, M. Wand, H.-P. Seidel, L. J. Guibas: Meshless Modeling of Deformable Shapes and their Motion. In: ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 2008.
    paper (4 MB), video (Youtube)
  • M. Wand, P. Jenke, Q. Huang, M. Bokeloh, L. Guibas, and A. Schilling: Reconstruction of Deforming Geometry from Time-Varying Point Clouds. In: Proc. 5th Eurographics Symposium on Geometry Processing, Barcelona, Spain, pp. 49-58, 2007.
    paper (0.6 MB), video (DivX, 36 MB)


Algorithms and Data Structures for Large Scene Editing

We consider the problem of handling large amounts of geometric data. We have developed a new data structure that allows for real-time editing and visualization of large out-of-core 3D data sets, with size limited only by available hard disc space. We have also developed an open and modular system architecture that uses this data structure as an abstract geometric data base to implement a real-time large scene editor application, supporting interactive local editing, various streaming geometry processing algorithms, and large animation sequences.

Key Publications

  • M. Wand, A. Berner, M. Bokeloh, A. Fleck, M. Hoffmann, P. Jenke, B. Maier, D. Staneker, A.Schilling:Interactive Editing of Large Point Clouds. In: Proc. Symposium on Point-Based Graphics (PBG 07), 2007.
    (3.9 MB), video (DivX, 46 MB)
  • M. Wand, A. Berner, M. Bokeloh, P. Jenke, A. Fleck, M. Hoffmann, B. Maier, D. Staneker, A.Schilling, H.-P. Seidel: Processing and Interactive Editing of Huge Point Clouds from 3D Scanners. In: Computer and Graphics, 2008.
  • Software: The XGRT system - this is a complete point cloud processing software framework with graphics user interface that can handle very large data sets interactively.
    Project page and download (binary & source code, GPL)

3D Reconstruction

In this project, we have investigated statistical shape spaces as a tool for surface reconstruction. We infer the most likely original shape given a noisy measurment (in the sense of maximizing the posterior propability density for a given statistic measurment model and user defined shape priors).

Key Publications

  • P. Jenke., M. Wand, M. Bokeloh, A. Schilling, W. Strasser: Bayesian Point Cloud Reconstruction. In: Computer Graphics forum 25(3), 379-388 (Proc. Eurographics 2006), 2006.
    paper (3.5 MB)
  • Q.-X. Huang, B. Adams, M. Wand: Bayesian Surface Reconstruction via Iterative Scan Alignment to an Optimized Prototype. In: Proc. 5th Eurographics Symposium on Geometry Processing, Barcelona, Spain, 2007.
    paper (21 MB)
Stochastic Synthesis of Complex 3D Models

Here we consider forward-modeling: We use a generative stochastical model to create objects procedurally. We develop a new hierarchical, bounded support subdivision, multi-channel geometry synthesis technique that is able to create complex, non-stationary fractal objects in an intuitive way. By specifying some simple multi-variate subdivision rules, models ranging from smooth patches to complex landscape models can be created. Due to a GPU implementation, the technique works in real-time, allowing to zoom into objects with virtually infinite detail.

Key Publication

  • M. Bokeloh., M. Wand: Hardware Accelerated Multi-Resolution Geometry Synthesis. In: Symposium on Interactive 3D Graphics and Games 2006.
    paper (4.6 MB), video, (DivX 24MB)


Ongoing Projects

since 2017: "Machine Learning for Multiscale Simulations", sponsored by the DFG collaborative research center (TRR) 146 "Multiscale Simulation Methods for Soft Matter Systems"

TRR146 logo TRR146 logo

Previous Funding

2016: "Big Data in Radiology: Quantitative Assessment of 3D Computer Tomography Image Data Bases" sponsored by the Center for Computational Science Mainz (CSM).

CSM logo

2012–2016: "Symmetry-based Shape Analysis and Modeling" sponsored by the Intel Visual Computing Institute.

ivci logo

2005–2013: Junior research group "Statistical Geometry Processing" sponsored by the Max-Planck-Center for Visual Computing and Communication.

symmetry-based shape analysis and modeling
2008–2013: Junior research group "Statistical Geometry Processing" sponsored by the Cluster of Excellence on Multi-Modal Computing and Interaction. symmetry-based shape analysis and modeling