Research map / 3D vision / Depth and stereo
VideoSfM: Exploiting Temporal Structure for Video-Based Structure-from-Motion
Zador Pataki, Paul-Edouard Sarlin, Marc Pollefeys
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 depth priors in global positioning (ablation) | VidMap · LaMAR | W-AUC full: 37.7 -> 88.5 | Improved |
| add depth priors in bundle adjustment (ablation) | VidMap · LaMAR | W-AUC full: 85.5 -> 88.5 | Improved |
| add per-image scale optimization (ablation) | VidMap · LaMAR | W-AUC full: 39.7 -> 88.5 | Improved |
| add metric scale prior (ablation) | VidMap · LaMAR | W-AUC full: 74.1 -> 88.5 | Improved |
| add loop closure edges (ablation) | VidMap · ETH3D-SLAM | AUC@5cm: 32.9 -> 51.4 | Improved |
| add loop closure edges (ablation) | VidMap · LaMAR | W-AUC full: 85.5 -> 88.5 | Improved |
| add provenance-dependent robust losses (ablation) | VidMap · LaMAR | W-AUC full: 79.9 -> 88.5 | Improved |
| add metric scale prior, on short sequences (ablation) | VidMap · ETH3D-SLAM | AUC@5cm: 52.2 -> 51.4 | No clear effect |
| add second graduated BA refinement pass (ablation) | VidMap · ETH3D-SLAM | AUC@5cm: 59.3 -> 67.5 | Improved |
| add second graduated BA refinement pass (ablation) | VidMap · EuRoC | AUC@5cm: 12.2 -> 22.2 | Improved |
| add depth-regularized relative pose (MDRP) (ablation) | VidMap · LaMAR-HGE | median WTE full (m): 0.45 -> 0.43 | No clear effect |
| use ground-truth calibration instead of estimated intrinsics | VidMap · ETH3D-SLAM | AUC@5cm: 51.4 -> 69.4 | 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.
- MegaSaM — MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos (CVPR 2025) · better on 2 of 2 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
- MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos (CVPR 2025 · similarity 0.90)
- Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos (ECCV 2026 · similarity 0.89)
- UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization (ECCV 2026 · similarity 0.89)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.87)
- Light3R-SfM: Towards Feed-forward Structure-from-Motion (CVPR 2025 · similarity 0.87)
- AnyMap: Learning a General Camera Model for Structure-from-Motion with Unknown Distortion in Dynamic Scenes (CVPR 2025 · similarity 0.87)
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.
