Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu
Home Research Areas Visual SLAM D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
research:vslam:d3vo [2020/06/15 09:37]
Nan Yang
research:vslam:d3vo [2020/06/15 10:06] (current)
Nan Yang
Line 9: Line 9:
  
 ==== Abstract ==== ==== Abstract ====
-{{:​research:​vslam:​d3vo:​d3vo-teaser.gif}}+{{:​research:​vslam:​d3vo:​d3vo-teaser-crop.gif}}
  
 We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. In particular, it aligns the training image pairs into similar lighting condition with predictive brightness transformation parameters. Besides, we model the photometric uncertainties of pixels on the input images, which improves the depth estimation accuracy and provides a learned weighting function for the photometric residuals in direct (feature-less) visual odometry. Evaluation results show that the proposed network outperforms state-of-the-art self-supervised depth estimation networks. D3VO tightly incorporates the predicted depth, pose and uncertainty into a direct visual odometry method to boost both the front-end tracking as well as the back-end non-linear optimization. We evaluate D3VO in terms of monocular visual odometry on both the KITTI odometry benchmark and the EuRoC MAV dataset. The results show that D3VO outperforms state-of-the-art traditional monocular VO methods by a large margin. It also achieves comparable results to state-of-the-art stereo/​LiDAR odometry on KITTI and to the state-of-the-art visual-inertial odometry on EuRoC MAV, while using only a single camera. We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. In particular, it aligns the training image pairs into similar lighting condition with predictive brightness transformation parameters. Besides, we model the photometric uncertainties of pixels on the input images, which improves the depth estimation accuracy and provides a learned weighting function for the photometric residuals in direct (feature-less) visual odometry. Evaluation results show that the proposed network outperforms state-of-the-art self-supervised depth estimation networks. D3VO tightly incorporates the predicted depth, pose and uncertainty into a direct visual odometry method to boost both the front-end tracking as well as the back-end non-linear optimization. We evaluate D3VO in terms of monocular visual odometry on both the KITTI odometry benchmark and the EuRoC MAV dataset. The results show that D3VO outperforms state-of-the-art traditional monocular VO methods by a large margin. It also achieves comparable results to state-of-the-art stereo/​LiDAR odometry on KITTI and to the state-of-the-art visual-inertial odometry on EuRoC MAV, while using only a single camera.

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de