Research map / 3D vision / 3D generation
Probabilistic Structure From Motion With Objects (PSfMO)
Paul Gay, Cosimo Rubino, Vaibhav Bansal, Alessio Del Bue
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 ShapeNet-derived category shape prior (SfMO to PSfMO) (ablation) | SfMO · ScanNet (1217 sequences) | mean O3D: 0.72 -> 0.82 | Improved |
| add ShapeNet shape prior (ablation) | SfMO · Synthetic ellipsoids with noisy ellipses | volume overlap O3D | Improved |
| add shape prior when detections are noise-free (ablation) | SfMO · Synthetic ellipsoids, no noise | volume overlap O3D | No clear effect |
| add shape prior under size errors versus rotation errors (ablation) | SfMO · Synthetic ellipsoids | volume overlap O3D | Mixed |
| add shape prior with all views used (ablation) | SfMO · KINECT dataset (five sequences) | qualitative ellipsoid quality | No clear effect |
| add shape prior with a reduced number of views (ablation) | SfMO · KINECT dataset (five sequences) | qualitative ellipsoid quality | Improved |
| add shape prior for low intra-class variability categories (ablation) | SfMO · ScanNet, trash bin versus table and couch | O3D | Mixed |
Closest papers by meaning
- Semantic Multi-View Stereo: Jointly Estimating Objects and Voxels (CVPR 2017 · similarity 0.87)
- Reconstruct Locally, Localize Globally: A Model Free Method for Object Pose Estimation (CVPR 2020 · similarity 0.87)
- Uncertainty-Driven 6D Pose Estimation of Objects and Scenes From a Single RGB Image (CVPR 2016 · similarity 0.86)
- Learning Category-Specific Deformable 3D Models for Object Reconstruction (TPAMI 2016 · similarity 0.86)
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · similarity 0.86)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.85)
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.
