LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
About
Recovering a dynamic 3D scene from a long monocular video is crucial for dense geometry, camera motion, and temporal correspondence to remain consistent in a shared coordinate system. Existing methods face two key challenges: (1) feed-forward reconstruction models provide accurate local predictions but are limited to short clips, and (2) long-range trackers preserve correspondences without producing dense sequence-level reconstruction. This paper presents LongDPM, a novel overlap-aware framework for scalable long-range monocular dynamic reconstruction. First, LongDPM processes long videos in overlapping chunks, keeping inference memory bounded by the chunk length. Second, it connects chunk-local coordinate systems through confidence-weighted registration with static-aware overlap abstraction. Third, it associates dynamic identities across chunk boundaries and fuses matched trajectories to recover coherent long-range 3D motion. Experimental results demonstrate that LongDPM achieves superior long-range reconstruction and tracking performance, reducing dense tracking EPE over V-DPM on PointOdyssey, Kubric-F, and Kubric-G, while obtaining the best TUM-dynamics ATE for camera pose estimation.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Camera pose estimation | TUM-dynamic | ATE0.012 | 205 | |
| Camera pose estimation | Sintel dataset | ATE0.078 | 35 | |
| Two-view tracking | PointOdyssey (test) | Tracking Error P0 (t1)0.027 | 9 | |
| Two-view tracking | Kubric-F (test) | Tracking Error P0 (t1)0.031 | 9 | |
| Two-view tracking | Kubric-G (test) | P0 (t1)0.043 | 9 | |
| Two-view tracking | Waymo (test) | Error P0 (t1)0.061 | 9 | |
| Dense 3D Tracking | PointOdyssey 10-frame snippets | EPE0.025 | 5 | |
| Dense 3D Tracking | Kubric-F (10-frame snippets) | Endpoint Error (EPE)0.021 | 5 | |
| Dense 3D Tracking | Kubric-G 10-frame snippets | Endpoint Error (EPE)0.029 | 5 | |
| Dense 3D Tracking | Waymo (10-frame snippets) | EPE0.044 | 5 |