Martin Garbade

Martin Garbade
University of Bonn | Uni Bonn · Institute for Computer Sciences

MSc Physics

About

13
Publications
4,132
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
952
Citations
Additional affiliations
November 2013 - present
University of Bonn
Position
  • PhD Student
Education
October 2010 - August 2012
University of Bonn
Field of study
  • Physics
October 2007 - September 2010
University of Bonn
Field of study
  • Physics

Publications

Publications (13)
Article
Full-text available
A holistic semantic scene understanding exploiting all available sensor modalities is a core capability to master self-driving in complex everyday traffic. To this end, we present the SemanticKITTI dataset that provides point-wise semantic annotations of Velodyne HDL-64E point clouds of the KITTI Odometry Benchmark. Together with the data, we also...
Conference Paper
Full-text available
Semantic scene understanding is important for various applications. In particular, self-driving cars need a fine-grained understanding of the surfaces and objects in their vicinity. Light detection and ranging (LiDAR) provides precise geometric information about the environment and is thus a part of the sensor suites of almost all self-driving cars...
Preprint
We address the task of 3D semantic scene completion, i.e. , given a single depth image, we predict the semantic labels and occupancy of voxels in a 3D grid representing the scene. In light of the recently introduced generative adversarial networks (GAN), our goal is to explore the potential of this model and the efficiency of various important desi...
Preprint
Full-text available
Semantic scene understanding is important for various applications. In particular, self-driving cars need a fine-grained understanding of the surfaces and objects in their vicinity. Light detection and ranging (LiDAR) provides precise geometric information about the environment and is thus a part of the sensor suites of almost all self-driving cars...
Chapter
While annotating objects in images is already time-consuming, annotating finer details like object parts or affordances of objects is even more tedious. Given the fact that large datasets with object annotations already exist, we address the question whether we can leverage such information to train a convolutional neural network for segmenting aff...
Article
Full-text available
We propose a new paradigm for advancing 3D semantic scene completion based on RGBD images. We introduce a two stream approach that uses RGB and depth as input channels to a 3D convolutional neural network. Our approach boosts the performance of semantic scene completion by a significant margin. We further provide a study on several input encoding s...
Conference Paper
Full-text available
In this work we propose to utilize information about human actions to improve pose estimation in monocular videos. To this end, we present a pictorial structure model that exploits high-level information about activities to incorporate higher-order part dependencies by modeling action specific appearance models and pose priors. However, instead of...
Conference Paper
Full-text available
Despite of the success of convolutional neural networks for semantic image segmentation, CNNs cannot be used for many applications due to limited computational resources. Even efficient approaches based on random forests are not efficient enough for real-time performance in some cases. In this work, we propose an approach based on superpixels and l...
Conference Paper
Full-text available
We evaluate the capabilities of the recently introduced NTraj+ features for action recognition based on 2d human pose on a variety of datasets. Inspired by the recent success of neural networks for computer vision tasks like image classification, we also explore their performance on the same action recognition tasks. Therefore we introduce two new...

Network

Cited By