Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
research:vslam:dvso [2018/08/24 14:51] yangn |
research:vslam:dvso [2019/03/03 17:03] yangn |
||
---|---|---|---|
Line 1: | Line 1: | ||
===== Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry ===== | ===== Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry ===== | ||
- | **Contact: | + | **Contact: |
+ | Oral presentation at ECCV 2018: [[https:// | ||
< | < | ||
src=" | src=" | ||
Line 9: | Line 10: | ||
==== Abstract ==== | ==== Abstract ==== | ||
- | Monocular visual odometry approaches that purely rely on geometric cues are prone to scale drift and require sufficient motion parallax in successive frames for motion estimation and 3D reconstruction. In this paper, we propose to leverage deep monocular depth prediction to overcome limitations of geometry-based monocular visual odometry. To this end, we incorporate deep depth predictions into DSO ([[: | + | Monocular visual odometry approaches that purely rely on geometric cues are prone to scale drift and require sufficient motion parallax in successive frames for motion estimation and 3D reconstruction. In this paper, we propose to leverage deep monocular depth prediction to overcome limitations of geometry-based monocular visual odometry. To this end, we incorporate deep depth predictions into [[: |
{{: | {{: | ||
Line 24: | Line 25: | ||
==== Results ==== | ==== Results ==== | ||
- | We quantitatively evaluate our StackNet with other state-of-the-art monocular depth prediction methods on the publicly available KITTI dataset. For DVSO, we evaluate its tracking accuracy on the KITTI odometry benchmark with other state-of-the-art monocular as well as stereo visual odometry systems. In the [[spezial:bib:yang2018dvso-supp.pdf|supplementary material]], we also show the generalization ability of StackNet as well as DVSO. | + | We quantitatively evaluate our StackNet with other state-of-the-art monocular depth prediction methods on the publicly available KITTI dataset. For DVSO, we evaluate its tracking accuracy on the KITTI odometry benchmark with other state-of-the-art monocular as well as stereo visual odometry systems. In the [[:research:vslam:dvso|supplementary material]], we also show the generalization ability of StackNet as well as DVSO. |
=== Monocular Depth Estimation === | === Monocular Depth Estimation === | ||
Line 40: | Line 41: | ||
{{: | {{: | ||
- | ==== Publication | + | ==== Downloads ==== |
+ | Trajectories of DVSO on KITTI 00-10: {{ : | ||
+ | |||
+ | ==== Publications | ||
< | < | ||
- | < | + | < |
</ | </ | ||