Research map / 3D vision / Depth and stereo
Multi-body Depth and Camera Pose Estimation from Multiple Views
Andrea Porfiri Dal Cin, Giacomo Boracchi, Luca Magri
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 |
|---|---|---|---|
| model multiple rigid motions with multi-body plane sweep (M=2 instead of M=1) (ablation) | multi-body plane sweep network · ETH3D (multi-body) | L1-inv: 0.11 -> 0.09 | Improved |
| model multiple rigid motions (M=3 instead of M=1) (ablation) | multi-body plane sweep network · Multi-body Unstructured | L1-inv: 0.21 -> 0.17 | Improved |
| use multi-body method versus Wang et al. on multi-body KITTI | Eigen MB split · KITTI Eigen MB | Abs Rel: 0.063 -> 0.057 | Improved |
| use multi-body method on static scenes versus Wang et al. | KITTI Eigen SfM · KITTI Eigen SfM (static) | Abs Rel: 0.034 -> 0.044 | Hurt |
| increase number of assumed motions M on static scenes (M=1 to M=4) (ablation) | multi-body plane sweep network · MVS, Scenes11, SUN3D (static) | L1-inv: 0.016 -> 0.026 (MVS) | Hurt |
| use monocular depth cues instead of DeMoN initialization | static MVS/Scenes11/SUN3D · MVS | L1-inv | Hurt |
| increase M from 1 to 4 on dynamic ETH3D (ablation) | multi-body plane sweep network · ETH3D (multi-body) | terr (deg): 9.58 -> 8.23 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DeepSfM — DeepSFM: Structure From Motion Via Deep Bundle Adjustment (ECCV 2020) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Deep Two-View Structure-From-Motion Revisited (CVPR 2021 · similarity 0.91)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.88)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.88)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.87)
- MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025 · similarity 0.87)
- Multi-view Reconstruction via SfM-guided Monocular Depth Estimation (CVPR 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.
