Research map / 3D vision / Depth and stereo
The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes
David Recasens, Martin R. Oswald, Marc Pollefeys, Javier Civera
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 |
|---|---|---|---|
| Use flow-based odometry that decomposes motion into camera motion and non-rigid deformation | Drunkard’s Odometry · Drunkard's Dataset | RPE | Improved |
| Use flow-based odometry that decomposes motion into camera motion and non-rigid deformation | Drunkard’s Odometry · Drunkard's Dataset, higher deformation levels | RPE | Improved |
| Use COLMAP instead of Drunkard’s Odometry | Drunkard’s Odometry · Drunkard's Dataset | ATE | Mixed |
| Train on deformable scenes rather than rigid scenes | Drunkard’s Odometry · Hamlyn scenes 1 and 17 | APTE | Improved |
| Apply Drunkard’s Odometry to a sharply moving sequence without recurrent near-loop closures | Drunkard’s Odometry · Hamlyn scene 17 | APTE | 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.
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · 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
- 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface (ICCV 2021 · similarity 0.86)
- Direct Sparse Odometry (TPAMI 2017 · similarity 0.86)
- 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians (CVPR 2025 · similarity 0.85)
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025 · similarity 0.85)
- SpatialTracker: Tracking Any 2D Pixels in 3D Space (CVPR 2024 · similarity 0.85)
- RDD: Robust Feature Detector and Descriptor using Deformable Transformer (CVPR 2025 · similarity 0.84)
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.
