1 code implementation • 9 Feb 2024 • Yue Tan, Olaf Wysocki, Ludwig Hoegner, Uwe Stilla
3D building models with facade details are playing an important role in many applications now.
1 code implementation • 9 Feb 2024 • Sophia Schwarz, Tanja Pilz, Olaf Wysocki, Ludwig Hoegner, Uwe Stilla
Point clouds and high-resolution 3D data have become increasingly important in various fields, including surveying, construction, and virtual reality.
1 code implementation • 9 Feb 2024 • Thomas Froech, Olaf Wysocki, Ludwig Hoegner, Uwe Stilla
We propose a new approach for the reconstruction of 3D fa\c{c}ade details.
no code implementations • 9 Feb 2024 • Olaf Wysocki, Ludwig Hoegner, Uwe Stilla
Although highly-detailed LoD3 building models reveal great potential in various applications, they have yet to be available.
1 code implementation • 10 May 2023 • Olaf Wysocki, Yan Xia, Magdalena Wysocki, Eleonora Grilli, Ludwig Hoegner, Daniel Cremers, Uwe Stilla
To this end, we leverage laser physics and 3D building model priors to probabilistically identify model conflicts.
1 code implementation • 14 Apr 2023 • Olaf Wysocki, Ludwig Hoegner, Uwe Stilla
Point clouds are widely regarded as one of the best dataset types for urban mapping purposes.
no code implementations • 10 Mar 2023 • Olaf Wysocki, Eleonora Grilli, Ludwig Hoegner, Uwe Stilla
The semantic voxels and conflicts are combined in a Bayesian network to classify and delineate fa\c{c}ade openings, which are reconstructed using a 3D model library.
1 code implementation • ICCV 2023 • Yan Xia, Mariia Gladkova, Rui Wang, Qianyun Li, Uwe Stilla, João F. Henriques, Daniel Cremers
CASSPR uses queries from one branch to try to match structures in the other branch, ensuring that both extract self-contained descriptors of the point cloud (rather than one branch dominating), but using both to inform the output global descriptor of the point cloud.
1 code implementation • 8 Mar 2022 • Yan Xia, Qiangqiang Wu, Wei Li, Antoni B. Chan, Uwe Stilla
Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking.
no code implementations • 28 May 2021 • Björn Borgmann, Volker Schatz, Marcus Hammer, Marcus Hebel, Michael Arens, Uwe Stilla
We present the current state of development of the sensor-equipped car MODISSA, with which Fraunhofer IOSB realizes a configurable experimental platform for hardware evaluation and software development in the context of mobile mapping and vehicle-related safety and protection.
no code implementations • 5 May 2021 • Rong Huang, Wei Yao, Yusheng Xu, Zhen Ye, Uwe Stilla
Registration is a fundamental but critical task in point cloud processing, which usually depends on finding element correspondence from two point clouds.
1 code implementation • 19 Apr 2021 • Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla
We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net.
no code implementations • 24 Dec 2020 • Rong Huang, Yusheng Xu, Uwe Stilla
We conducted comprehensive experiments on two ALS point cloud datasets to evaluate the performance of our proposed framework.
1 code implementation • CVPR 2021 • Yan Xia, Yusheng Xu, Shuang Li, Rui Wang, Juan Du, Daniel Cremers, Uwe Stilla
We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors.
Ranked #5 on 3D Place Recognition on Oxford RobotCar Dataset (AR@1% metric)
1 code implementation • 8 Aug 2020 • Yan Xia, Yusheng Xu, Cheng Wang, Uwe Stilla
Moreover, a new refiner module is also presented to preserve the vehicle details from inputs and refine the complete outputs with fine-grained information.
no code implementations • ECCV 2018 • Niclas Zeller, Franz Quint, Uwe Stilla
The method is tested based on a versatile dataset consisting of challenging indoor and outdoor sequences and is compared to state-of-the-art monocular and stereo approaches.
no code implementations • 24 Jul 2018 • Niclas Zeller, Franz Quint, Uwe Stilla
We present a new dataset to evaluate monocular, stereo, and plenoptic camera based visual odometry algorithms.
1 code implementation • 6 Nov 2017 • Dimitrios Marmanis, Wei Yao, Fathalrahman Adam, Mihai Datcu, Peter Reinartz, Konrad Schindler, Jan Dirk Wegner, Uwe Stilla
Very High Spatial Resolution (VHSR) large-scale SAR image databases are still an unresolved issue in the Remote Sensing field.
1 code implementation • 5 Dec 2016 • Dimitrios Marmanis, Konrad Schindler, Jan Dirk Wegner, Silvano Galliani, Mihai Datcu, Uwe Stilla
We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries.