M.Sc. Jonas Schult
Room 122
Phone: +49 241 80 20 765
Fax: +49 241 80 22 731
Email: schult (at) vision.rwth-aachen.de


DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes

Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020 (Oral)

We propose DualConvMesh-Nets (DCM-Net) a family of deep hierarchical convolutional networks over 3D geometric data that combines two types of convolutions. The first type, geodesic convolutions, defines the kernel weights over mesh surfaces or graphs. That is, the convolutional kernel weights are mapped to the local surface of a given mesh. The second type, Euclidean convolutions, is independent of any underlying mesh structure. The convolutional kernel is applied on a neighborhood obtained from a local affinity representation based on the Euclidean distance between 3D points. Intuitively, geodesic convolutions can easily separate objects that are spatially close but have disconnected surfaces, while Euclidean convolutions can represent interactions between nearby objects better, as they are oblivious to object surfaces. To realize a multi-resolution architecture, we borrow well-established mesh simplification methods from the geometry processing domain and adapt them to define mesh-preserving pooling and unpooling operations. We experimentally show that combining both types of convolutions in our architecture leads to significant performance gains for 3D semantic segmentation, and we report competitive results on three scene segmentation benchmarks.

» Show BibTeX

author = {Jonas Schult* and
Francis Engelmann* and
Theodora Kontogianni and
Bastian Leibe},
title = {{DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes}},
booktitle = {{IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}},
year = {2020}

3D-BEVIS: Birds-Eye-View Instance Segmentation

Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe
German Conference on Pattern Recognition (GCPR) 2019

Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the task of instance segmentation is less explored. In this work, we present 3D-BEVIS, a deep learning framework for 3D semantic instance segmentation on point clouds. Following the idea of previous proposal-free instance segmentation approaches, our model learns a feature embedding and groups the obtained feature space into semantic instances. Current point-based methods scale linearly with the number of points by processing local sub-parts of a scene individually. However, to perform instance segmentation by clustering, globally consistent features are required. Therefore, we propose to combine local point geometry with global context information from an intermediate bird's-eye view representation.

» Show BibTeX

title = {{3D-BEVIS: Birds-Eye-View Instance Segmentation}},
author = {Elich, Cathrin and Engelmann, Francis and Schult, Jonas and Kontogianni, Theodora and Leibe, Bastian},
booktitle = {{German Conference on Pattern Recognition (GCPR)}},
year = {2019}

Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

Francis Engelmann, Theodora Kontogianni, Jonas Schult, Bastian Leibe
IEEE European Conference on Computer Vision (ECCV'18), GMDL Workshop

In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds. Compared to previous work, we introduce grouping techniques which define point neighborhoods in the initial world space and the learned feature space. Neighborhoods are important as they allow to compute local or global point features depending on the spatial extend of the neighborhood. Additionally, we incorporate dedicated loss functions to further structure the learned point feature space: the pairwise distance loss and the centroid loss. We show how to apply these mechanisms to the task of 3D semantic segmentation of point clouds and report state-of-the-art performance on indoor and outdoor datasets.

» Show BibTeX

author = {Francis Engelmann and
Theodora Kontogianni and
Jonas Schult and
Bastian Leibe},
title = {Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds},
booktitle = {{IEEE} European Conference on Computer Vision, GMDL Workshop, {ECCV}},
year = {2018}

Disclaimer Home Visual Computing institute RWTH Aachen University