Title | ||
---|---|---|
StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks |
Abstract | ||
---|---|---|
Robust point cloud registration in real-time is an important prerequisite for many mapping and localization algorithms. Traditional methods like ICP tend to fail without good initialization, insufficient overlap or in the presence of dynamic objects. Modern deep learning based registration approaches present much better results, but suffer from a heavy runtime. We overcome these drawbacks by intro... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPR46437.2021.00038 | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Keywords | DocType | ISSN |
Deep learning,Three-dimensional displays,Runtime,Laser radar,Pose estimation,Pipelines,Transformers | Conference | 1063-6919 |
ISBN | Citations | PageRank |
978-1-6654-4509-2 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kai Fischer | 1 | 0 | 0.68 |
Martin Simon | 2 | 33 | 8.42 |
Florian Olsner | 3 | 0 | 0.34 |
Stefan Milz | 4 | 17 | 7.74 |
Horst-Michael Gross | 5 | 761 | 92.05 |
Patrick Mäder | 6 | 492 | 36.96 |