Research map / Learning theory and algorithms / Optimal transport
Synchronizing Probability Measures on Rotations via Optimal Transport
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 10 particles and optimize their weights instead of using a single particle (ablation) | RPGD measure synchronization · 1D-SFM | median angular error: 2.26 -> 2.16 | Mixed |
| Use the geodesic ground metric rather than the Euclidean metric (ablation) | Measure synchronization on noisy synthetic data · Synthetic data | error | Helped |
| Increase relative-pose noise beyond σ>0.01 (ablation) | Measure synchronization · Synthetic data | attained error: σ>0.01 | Hurt |
| Overestimate the number of absolute particles (ablation) | Measure synchronization · Synthetic data | recovery quality: K_i>9 | Helped |
| Increase graph completeness to 50% (ablation) | Measure synchronization · Synthetic data | result quality: 50% | Helped |
| Use Sinkhorn loss instead of MMD loss (ablation) | RPGD measure synchronization · Synthetic data | minimum distance | Helped |
| Use MMD with a Euclidean kernel (ablation) | RPGD measure synchronization · Synthetic data | convergence | Hurt |
Closest papers by meaning
- Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope (CVPR 2019 · similarity 0.88)
- Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor (NeurIPS 2024 · similarity 0.86)
- Robust Angular Synchronization via Directed Graph Neural Networks (ICLR 2024 · similarity 0.84)
- Efficient Detection of Long Consistent Cycles and its Application to Distributed Synchronization (CVPR 2024 · similarity 0.84)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.83)
- Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization (NeurIPS 2025 · similarity 0.83)
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.