Research map / 3D vision / Depth and stereo
Stereo DSO: Large-Scale Direct Sparse Visual Odometry With Stereo Cameras
Rui Wang, Martin Schworer, Daniel Cremers
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add static stereo constraints with coupling factor lambda=1,2 (ablation) | Stereo DSO · KITTI Seq. 06 | translational and rotational error | Improved |
| increase static stereo weighting beyond lambda>3 (ablation) | Stereo DSO · KITTI Seq. 06 | translational and rotational error | Hurt |
| use Stereo DSO instead of Stereo LSD-VO | Stereo DSO · KITTI training set | rotational RMSE (deg/100m): 0.40 -> 0.20 | Improved |
| use Stereo DSO instead of ORB-SLAM2 without loop closure | Stereo DSO · KITTI training set | rotational RMSE (deg/100m): 0.26 -> 0.20 | Improved |
| use Stereo DSO instead of ORB-SLAM2 without loop closure | Stereo DSO · KITTI training set | translational RMSE (%): 0.81 -> 0.84 | Mixed |
| use Stereo DSO VO instead of SLAM with loop closure (ORB-SLAM2, LSD-SLAM) | Stereo DSO · KITTI testing set (Seq. 11-21) | translational and rotational error | Improved |
| initialize depth with static stereo matching instead of 0-to-infinity range for candidate points (ablation) | Stereo DSO · KITTI | tracking accuracy | Improved |
| add fixed-baseline stereo to monocular DSO | Stereo DSO · KITTI training sequences | scale drift | Improved |
| use stereo DSO with affine brightness modeling under strong brightness change | Stereo DSO · Cityscapes | tracking failure | No clear effect |
Later papers that compared with this method
2 later accepted papers report Stereo DSO as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry (CVPR 2020 · better on 1 of 1 shared result)
- Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry (ECCV 2018 · better on 1 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Direct Sparse Odometry (TPAMI 2017 · similarity 0.91)
- Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry (ECCV 2018 · similarity 0.90)
- Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction (CVPR 2018 · similarity 0.90)
- Direct Sparse Odometry With Rolling Shutter (ECCV 2018 · similarity 0.89)
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (CVPR 2024 · similarity 0.86)
- Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
