Research map / 3D vision / Face and shape
On Geometric Alignment in Low Doubling Dimension
Hu Ding, Mingquan Ye
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 |
|---|---|---|---|
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment on the random dataset · Random dataset | Time (s): 1418.2 -> 48.7 | Improved |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment on the random dataset · Random dataset | EMD: 0.933 -> 0.948 | Hurt |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · sp-en | Time (s): 100.5 -> 3.4 | Improved |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · sp-en | EMD: 0.820 -> 0.989 | Hurt |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · it-en | Time (s): 162.6 -> 5.4 | Improved |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · it-en | EMD: 0.847 -> 0.983 | Hurt |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · ja-ch | Time (s): 67.0 -> 1.6 | Improved |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · ja-ch | EMD: 0.836 -> 0.991 | Hurt |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · tu-en | Time (s): 287.0 -> 10.1 | Improved |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · tu-en | EMD: 0.839 -> 0.982 | Hurt |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · ch-en | Time (s): 51.6 -> 1.9 | Improved |
| Compress point sets to γ=1/50 rather than using no compression | Geometric alignment · ch-en | EMD: 0.842 -> 1.014 | Hurt |
Closest papers by meaning
- Unsupervised Manifold Alignment with Joint Multidimensional Scaling (ICLR 2023 · similarity 0.83)
- Benchmarking PhD-Level Coding in 3D Geometric Computer Vision (CVPR 2026 · similarity 0.83)
- HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching (ICCV 2019 · similarity 0.83)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.83)
- Partial-to-Partial Shape Matching with Geometric Consistency (CVPR 2024 · similarity 0.83)
- Object-level Geometric Structure Preserving for Natural Image Stitching (AAAI 2025 · similarity 0.82)
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.
