Research map / Video / Video segmentation and tracking
StreamVLO: Streaming Visual-LiDAR Odometry with Cumulative Drift Compensation
Mengmeng Liu, Jiuming Liu, Michael Ying Yang, Chaokang Jiang, Jiangtao Li, Yunpeng Zhang, Hesheng Wang, Francesco Nex, Hao Cheng
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 unified MMG spatio-temporal correlation (ablation) | StreamVLO · KITTI seq 07-10 | t_rel (%): 0.70 -> 0.59 | Improved |
| add Cumulative Drift Compensation (ablation) | StreamVLO · KITTI seq 07-10 | t_rel (%): 0.70 -> 0.59 | Improved |
| add Keypoint-Aware Auxiliary Loss (winner-takes-all) (ablation) | StreamVLO · KITTI seq 07-10 | t_rel (%): 0.67 -> 0.59 | Improved |
| add Cumulative Drift Compensation (ablation) | StreamVLO · KITTI seq 07-10 | r_rel (deg/100m): 0.36 -> 0.29 | Improved |
| use deformable Mamba fusion instead of attention fusion (ablation) | StreamVLO · KITTI seq 07-10 | t_rel (%) / latency: 0.80 -> 0.59; 171 ms -> 74 ms | Improved |
| use deformable Mamba fusion instead of deformable attention (Deform DETR) (ablation) | StreamVLO · KITTI seq 07-10 | t_rel (%): 0.65 -> 0.59 | Improved |
| use deformable Mamba fusion instead of CNN fusion (ablation) | StreamVLO · KITTI seq 07-10 | latency (ms): 71 -> 74 ms latency; t_rel 0.81 -> 0.59 | Mixed |
| train on KITTI and test on Argoverse (cross-dataset) | StreamVLO vs DVLO · Argoverse | ATE (m): 0.073 -> 0.097 (+32.9%) vs DVLO 0.103 -> 0.187 (+81.6%) | Hurt |
| use StreamVLO instead of DVLO in high-dynamics scenes | KITTI · KITTI high dynamics | t_rel (%): 1.47 -> 0.77 | Improved |
Closest papers by meaning
- DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment (ECCV 2024 · similarity 0.87)
- LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving (CVPR 2026 · similarity 0.87)
- DiffLO: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement (CVPR 2025 · similarity 0.86)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.86)
- LightLoc: Learning Outdoor LiDAR Localization at Light Speed (CVPR 2025 · similarity 0.85)
- Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (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.
