Moritz Ibing, M.Sc.
Room 107
Phone: +49 241 8021807
Fax: +49 241 8022899
Email: ibing@cs.rwth-aachen.de


3D Shape Generation with Grid-based Implicit Functions

Moritz Ibing, Isaak Lim, Leif Kobbelt
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.

» Show BibTeX

@inproceedings {ibing20213Dshape,
title = {3D Shape Generation with Grid-based Implicit Functions},
author = {Ibing, Moritz and Lim, Isaak and Kobbelt, Leif},
booktitle = {IEEE Computer Vision and Pattern Recognition (CVPR)},
pages = {},
year = {2021}

A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization

Isaak Lim, Moritz Ibing, Leif Kobbelt
Eurographics Symposium on Geometry Processing 2019

Automatic synthesis of high quality 3D shapes is an ongoing and challenging area of research. While several data-driven methods have been proposed that make use of neural networks to generate 3D shapes, none of them reach the level of quality that deep learning synthesis approaches for images provide. In this work we present a method for a convolutional point cloud decoder/generator that makes use of recent advances in the domain of image synthesis. Namely, we use Adaptive Instance Normalization and offer an intuition on why it can improve training. Furthermore, we propose extensions to the minimization of the commonly used Chamfer distance for auto-encoding point clouds. In addition, we show that careful sampling is important both for the input geometry and in our point cloud generation process to improve results. The results are evaluated in an auto-encoding setup to offer both qualitative and quantitative analysis. The proposed decoder is validated by an extensive ablation study and is able to outperform current state of the art results in a number of experiments. We show the applicability of our method in the fields of point cloud upsampling, single view reconstruction, and shape synthesis.

» Show BibTeX

author = "Lim, Isaak and Ibing, Moritz and Kobbelt, Leif",
title = "A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization",
journal = "Computer Graphics Forum",
volume = 38,
number = 5,
year = 2019

Scale-Invariant Directional Alignment of Surface Parametrizations

Marcel Campen, Moritz Ibing, Hans-Christian Ebke, Denis Zorin, Leif Kobbelt
Eurographics Symposium on Geometry Processing 2016

Various applications of global surface parametrization benefit from the alignment of parametrization isolines with principal curvature directions. This is particularly true for recent parametrization-based meshing approaches, where this directly translates into a shape-aware edge flow, better approximation quality, and reduced meshing artifacts. Existing methods to influence a parametrization based on principal curvature directions suffer from scale-dependence, which implies the necessity of parameter variation, or try to capture complex directional shape features using simple 1D curves. Especially for non-sharp features, such as chamfers, fillets, blends, and even more for organic variants thereof, these abstractions can be unfit. We present a novel approach which respects and exploits the 2D nature of such directional feature regions, detects them based on coherence and homogeneity properties, and controls the parametrization process accordingly. This approach enables us to provide an intuitive, scale-invariant control parameter to the user. It also allows us to consider non-local aspects like the topology of a feature, enabling further improvements. We demonstrate that, compared to previous approaches, global parametrizations of higher quality can be generated without user intervention.

» Show BibTeX

author = "Campen, Marcel and Ibing, Moritz and Ebke, Hans-Christian and Zorin, Denis and Kobbelt, Leif",
title = "Scale-Invariant Directional Alignment of Surface Parametrizations",
journal = "Computer Graphics Forum",
volume = 35,
number = 5,
year = 2016

Disclaimer Home Visual Computing institute RWTH Aachen University