Search Results for author: Leif Kobbelt

Found 12 papers, 2 papers with code

Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences

no code implementations24 Nov 2021 Moritz Ibing, Gregor Kobsik, Leif Kobbelt

Autoregressive models have proven to be very powerful in NLP text generation tasks and lately have gained popularity for image generation as well.

3D Shape Generation Image Generation +1

Intuitive Shape Editing in Latent Space

no code implementations24 Nov 2021 Tim Elsner, Moritz Ibing, Victor Czech, Julius Nehring-Wirxel, Leif Kobbelt

We evaluate our method by comparing to state-of-the-art data-driven shape editing methods.

3D Shape Generation with Grid-based Implicit Functions

no code implementations CVPR 2021 Moritz Ibing, Isaak Lim, Leif Kobbelt

To remedy these issues, we propose to train the GAN on grids (i. e. each cell covers a part of a shape).

3D Shape Generation

Highly accurate digital traffic recording as a basis for future mobility research: Methods and concepts of the research project HDV-Mess

no code implementations8 Jun 2021 Laurent Kloeker, Fabian Thomsen, Lutz Eckstein, Philip Trettner, Tim Elsner, Julius Nehring-Wirxel, Kersten Schuster, Leif Kobbelt, Michael Hoesch

The research project HDV-Mess aims at a currently missing, but very crucial component for addressing important challenges in the field of connected and automated driving on public roads.

Fast Exact Booleans for Iterated CSG using Octree-Embedded BSPs

no code implementations3 Mar 2021 Julius Nehring-Wirxel, Philip Trettner, Leif Kobbelt

We present octree-embedded BSPs, a volumetric mesh data structure suited for performing a sequence of Boolean operations (iterated CSG) efficiently.

Computational Geometry Graphics

SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform

1 code implementation22 Oct 2020 Cheng Lin, Lingjie Liu, Changjian Li, Leif Kobbelt, Bin Wang, Shiqing Xin, Wenping Wang

Segmenting arbitrary 3D objects into constituent parts that are structurally meaningful is a fundamental problem encountered in a wide range of computer graphics applications.

PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models

1 code implementation15 Oct 2019 Lin Gao, Ling-Xiao Zhang, Hsien-Yu Meng, Yi-Hui Ren, Yu-Kun Lai, Leif Kobbelt

In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape.

Symmetry Detection

A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization

no code implementations27 Jun 2019 Isaak Lim, Moritz Ibing, Leif Kobbelt

In addition, we show that careful sampling is important both for the input geometry and in our point cloud generation process to improve results.

Image Generation Point Cloud Generation

A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes

no code implementations18 Sep 2018 Isaak Lim, Alexander Dielen, Marcel Campen, Leif Kobbelt

The question of representation of 3D geometry is of vital importance when it comes to leveraging the recent advances in the field of machine learning for geometry processing tasks.

Learning to Reconstruct High-quality 3D Shapes with Cascaded Fully Convolutional Networks

no code implementations ECCV 2018 Yan-Pei Cao, Zheng-Ning Liu, Zheng-Fei Kuang, Leif Kobbelt, Shi-Min Hu

We present a data-driven approach to reconstructing high-resolution and detailed volumetric representations of 3D shapes.

Sparse Data Driven Mesh Deformation

no code implementations5 Sep 2017 Lin Gao, Yu-Kun Lai, Jie Yang, Ling-Xiao Zhang, Leif Kobbelt, Shihong Xia

This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied.

Graphics

Efficient Computation of Shortest Path-Concavity for 3D Meshes

no code implementations CVPR 2013 Henrik Zimmer, Marcel Campen, Leif Kobbelt

Lien et al. [16] proposed two point-wise concavity measures in the context of Approximate Convex Decompositions of polygons measuring the distance from a point to the polygon's convex hull: an accurate Shortest Path-Concavity (SPC) measure and a Straight Line-Concavity (SLC) approximation of the same.

Cannot find the paper you are looking for? You can Submit a new open access paper.