{"ID":2869159,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.14636","arxiv_id":"2509.14636","title":"BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots","abstract":"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.","short_abstract":"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 l...","url_abs":"https://arxiv.org/abs/2509.14636","url_pdf":"https://arxiv.org/pdf/2509.14636v1","authors":"[\"Yufei Wei\",\"Wangtao Lu\",\"Sha Lu\",\"Chenxiao Hu\",\"Fuzhang Han\",\"Rong Xiong\",\"Yue Wang\"]","published":"2025-09-18T05:29:32Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}