Research map / 3D vision / Depth and stereo
VSO: Visual Semantic Odometry
Konstantinos-Nektarios Lianos, Johannes L. Schonberger, Marc Pollefeys, Torsten Sattler
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 semantic constraints | ORB-SLAM2 (stereo) · KITTI mean RPE | translational RPE (%): 1.15 -> 1.09 | Improved |
| add semantic constraints | PhotoBundle · KITTI mean RPE | translational RPE (%): 1.51 -> 1.28 | Improved |
| add semantic constraints | ORB-SLAM2 and PhotoBundle · KITTI mean RPE | rotational RPE (deg/100m): 0.33 -> 0.33 | No clear effect |
| add semantic constraints | mono-ORB-SLAM2 · KITTI ATE | ATE (m): 56 -> 45 | Improved |
| add semantic constraints | mono-ORB-SLAM2 · KITTI mean ATE | ATE (m): 9.06m mean reduction | Improved |
| add semantic constraints | ORB-SLAM2 and PhotoBundle · KITTI ATE | ATE (m): 0.55m and 0.51m mean reduction | Improved |
| add semantic constraints (ground-truth labels) | mono-ORB-SLAM2 · P4B seq 044 | ATE (m): 6.0 -> 3.0 | Improved |
| add semantic constraints | ORB-SLAM2 · KITTI seq 01 | translational RPE (%): 1.79 -> 1.95 | Hurt |
| add semantic constraints | ORB-SLAM2 · KITTI seq 04 (moving car in front) | translational RPE (%): 1.19 -> 1.30 | Hurt |
| exclude the car class from semantic optimization (ablation) | ORB-SLAM2 + semantics · KITTI seq 04 | translational RPE (%): 1.30 -> 1.23 | Improved |
| add semantic constraints | ORB-SLAM2 · KITTI seq 10 (poor segmentation) | translational RPE (%): 1.25 -> 1.28 | Hurt |
| increase uncertainty sigma on poorly segmented sequences (ablation) | ORB-SLAM2 + semantics · KITTI seq 10 | RPE | Improved |
Closest papers by meaning
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (CVPR 2024 · similarity 0.89)
- Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (CVPR 2024 · similarity 0.88)
- DiffLO: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement (CVPR 2025 · similarity 0.87)
- Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection (ECCV 2022 · similarity 0.87)
- ZeroVO: Visual Odometry with Minimal Assumptions (CVPR 2025 · similarity 0.87)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.86)
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.
