BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918143418433536 |
|---|---|
| author | Wei, Yufei Lu, Wangtao Lu, Sha Hu, Chenxiao Han, Fuzhang Xiong, Rong Wang, Yue |
| author_facet | Wei, Yufei Lu, Wangtao Lu, Sha Hu, Chenxiao Han, Fuzhang Xiong, Rong Wang, Yue |
| contents | Bird's-Eye-View (BEV) representation offers a metric-scaled planar workspace, facilitating the simplification of 6-DoF ego-motion to a more robust 3-DoF model for monocular visual odometry (MVO) in intelligent transportation systems. However, existing BEV methods suffer from sparse supervision signals and information loss during perspective-to-BEV projection. We present BEV-ODOM2, an enhanced framework addressing both limitations without additional annotations. Our approach introduces: (1) dense BEV optical flow supervision constructed from 3-DoF pose ground truth for pixel-level guidance; (2) PV-BEV fusion that computes correlation volumes before projection to preserve 6-DoF motion cues while maintaining scale consistency. The framework employs three supervision levels derived solely from pose data: dense BEV flow, 5-DoF for the PV branch, and final 3-DoF output. Enhanced rotation sampling further balances diverse motion patterns in training. Extensive evaluation on KITTI, NCLT, Oxford, and our newly collected ZJH-VO multi-scale dataset demonstrates state-of-the-art performance, achieving 40 improvement in RTE compared to previous BEV methods. The ZJH-VO dataset, covering diverse ground vehicle scenarios from underground parking to outdoor plazas, is publicly available to facilitate future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14636 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots Wei, Yufei Lu, Wangtao Lu, Sha Hu, Chenxiao Han, Fuzhang Xiong, Rong Wang, Yue Robotics Bird's-Eye-View (BEV) representation offers a metric-scaled planar workspace, facilitating the simplification of 6-DoF ego-motion to a more robust 3-DoF model for monocular visual odometry (MVO) in intelligent transportation systems. However, existing BEV methods suffer from sparse supervision signals and information loss during perspective-to-BEV projection. We present BEV-ODOM2, an enhanced framework addressing both limitations without additional annotations. Our approach introduces: (1) dense BEV optical flow supervision constructed from 3-DoF pose ground truth for pixel-level guidance; (2) PV-BEV fusion that computes correlation volumes before projection to preserve 6-DoF motion cues while maintaining scale consistency. The framework employs three supervision levels derived solely from pose data: dense BEV flow, 5-DoF for the PV branch, and final 3-DoF output. Enhanced rotation sampling further balances diverse motion patterns in training. Extensive evaluation on KITTI, NCLT, Oxford, and our newly collected ZJH-VO multi-scale dataset demonstrates state-of-the-art performance, achieving 40 improvement in RTE compared to previous BEV methods. The ZJH-VO dataset, covering diverse ground vehicle scenarios from underground parking to outdoor plazas, is publicly available to facilitate future research. |
| title | BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.14636 |