Wang, J;
Runz, M;
De Agapito Vicente, L;
(2022)
DSP-SLAM: object oriented SLAM with deep shape priors.
In:
2021 International Conference on 3D Vision (3DV).
IEEE
(In press).
Preview |
Text
DSP-SLAM_full.pdf - Accepted Version Download (18MB) | Preview |
Abstract
We propose DSP-SLAM, an object-oriented SLAM system that builds a rich and accurate joint map of dense 3D models for foreground objects, and sparse landmark points to represent the background. DSP-SLAM takes as input the 3D point cloud reconstructed by a feature-based SLAM system and equips it with the ability to enhance its sparse map with dense reconstructions of detected objects. Objects are detected via semantic instance segmentation, and their shape and pose is estimated using category-specific deep shape embeddings as priors, via a novel second order optimization. Our object-aware bundle adjustment builds a pose-graph to jointly optimize camera poses, object locations and feature points. DSP-SLAM can operate at 10 frames per second on 3 different input modalities: monocular, stereo, or stereo+LiDAR. We demonstrate DSP-SLAM operating at almost frame rate on monocular-RGB sequences from the Freiburg and Redwood-OS datasets, and on stereo+LiDAR sequences on the KITTI odometry dataset showing that it achieves high-quality full object reconstructions, even from partial observations, while maintaining a consistent global map. Our evaluation shows improvements in object pose and shape reconstruction with respect to recent deep prior-based reconstruction methods and reductions in camera tracking drift on the KITTI dataset.
| Type: | Proceedings paper |
|---|---|
| Title: | DSP-SLAM: object oriented SLAM with deep shape priors |
| Event: | 2021 International Conference on 3D Vision |
| Location: | UK/Virtual |
| Dates: | 01 December 2021 - 03 December 2021 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/3DV53792.2021.00143 |
| Publisher version: | http://doi.org/10.1109/3DV53792.2021.00143 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10141013 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
