header

Welcome


bdrp


Welcome to the Computer Graphics Group at RWTH Aachen University!

The research and teaching activities at our institute focus on geometry acquisition and processing, on interactive visualization, and on related areas such as computer vision, photo-realistic image synthesis, and ultra high speed multimedia data transmission.

In our projects we are cooperating with various industry companies as well as with academic research groups around the world. Results are published and presented at high-profile conferences and symposia. Additional funding sources, among others, are the Deutsche Forschungsgemeinschaft and the European Union.

News

Prof. Kobbelt will be on sabbatical (Forschungssemester) during the winter semester 2021.

Please note that the lecture Basic Techniques in Computer Graphics will only be held in Bonn. Our seminars and practical courses take place as usual.

July 16, 2021

Our papers Surface Map Homology Inference and Geodesic Distance Computation via Virtual Source Propagation received best paper awards (1st and 2nd place) at the Eurographics Symposium on Geometry Processing 2021.

July 16, 2021

We have four papers at SGP 2021:

June 30, 2021

We have a paper on compression of textured point clouds at HPG 2021.

June 8, 2021

We have a paper on Quadric CSG at HPG 2021.

June 8, 2021

We have a paper on Shape Generation at CVPR 2021.

May 20, 2021

Recent Publications

pubimg
3D Shape Generation with Grid-based Implicit Functions

IEEE Conference on Computer Vision and Pattern Recognition

Previous approaches to generate shapes in a 3D setting train a GAN on the latent space of an autoencoder (AE). Even though this produces convincing results, it has two major shortcomings. As the GAN is limited to reproduce the dataset the AE was trained on, we cannot reuse a trained AE for novel data. Furthermore, it is difficult to add spatial supervision into the generation process, as the AE only gives us a global representation. To remedy these issues, we propose to train the GAN on grids (i.e. each cell covers a part of a shape). In this representation each cell is equipped with a latent vector provided by an AE. This localized representation enables more expressiveness (since the cell-based latent vectors can be combined in novel ways) as well as spatial control of the generation process (e.g. via bounding boxes). Our method outperforms the current state of the art on all established evaluation measures, proposed for quantitatively evaluating the generative capabilities of GANs. We show limitations of these measures and propose the adaptation of a robust criterion from statistical analysis as an alternative.

fadeout
 
pubimg
Learning Direction Fields for Quad Mesh Generation

Eurographics Symposium on Geometry Processing 2021

State of the art quadrangulation methods are able to reliably and robustly convert triangle meshes into quad meshes. Most of these methods rely on a dense direction field that is used to align a parametrization from which a quad mesh can be extracted. In this context, the aforementioned direction field is of particular importance, as it plays a key role in determining the structure of the generated quad mesh. If there are no user-provided directions available, the direction field is usually interpolated from a subset of principal curvature directions. To this end, a number of heuristics that aim to identify significant surface regions have been proposed. Unfortunately, the resulting fields often fail to capture the structure found in meshes created by human experts. This is due to the fact that experienced designers can leverage their domain knowledge in order to optimize a mesh for a specific application. In the context of physics simulation, for example, a designer might prefer an alignment and local refinement that facilitates a more accurate numerical simulation. Similarly, a character artist may prefer an alignment that makes the resulting mesh easier to animate. Crucially, this higher level domain knowledge cannot be easily extracted from local curvature information alone. Motivated by this issue, we propose a data-driven approach to the computation of direction fields that allows us to mimic the structure found in existing meshes, which could originate from human experts or other sources. More specifically, we make use of a neural network that aggregates global and local shape information in order to compute a direction field that can be used to guide a parametrization-based quad meshing method. Our approach is a first step towards addressing this challenging problem with a fully automatic learning-based method. We show that compared to classical techniques our data-driven approach combined with a robust model-driven method, is able to produce results that more closely exhibit the ground truth structure of a synthetic dataset (i.e. a manually designed quad mesh template fitted to a variety of human body types in a set of different poses).

fadeout
 
pubimg
Simpler Quad Layouts using Relaxed Singularities

Eurographics Symposium on Geometry Processing 2021

A common approach to automatic quad layout generation on surfaces is to, in a first stage, decide on the positioning of irregular layout vertices, followed by finding sensible layout edges connecting these vertices and partitioning the surface into quadrilateral patches in a second stage. While this two-step approach reduces the problem's complexity, this separation also limits the result quality. In the worst case, the set of layout vertices fixed in the first stage without consideration of the second may not even permit a valid quad layout. We propose an algorithm for the creation of quad layouts in which the initial layout vertices can be adjusted in the second stage. Whenever beneficial for layout quality or even validity, these vertices may be moved within a prescribed radius or even be removed. Our algorithm is based on a robust quantization strategy, turning a continuous T-mesh structure into a discrete layout. We show the effectiveness of our algorithm on a variety of inputs.

fadeout
Disclaimer Home Visual Computing institute RWTH Aachen University