Research map / Learning theory and algorithms / Prediction and decision losses
Conformal Surface Alignment With Optimal Mobius Search
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 globally optimal Möbius Search instead of brute-force search | Conformal alignment of Human01–Human04 · Human01–Human04 (N1, N2 = 100) | Qbnb: 30 -> 40 | Helped |
| Use globally optimal Möbius Search instead of brute-force search | Conformal alignment of Gorilla167335–Gorilla167336 · Gorilla167335–Gorilla167336 (N1, N2 = 100) | Qbnb: 66 -> 68 | Helped |
| Use globally optimal Möbius Search instead of brute-force search | Conformal alignment of Chimpanzee51376–Chimpanzee51379 · Chimpanzee51376–Chimpanzee51379 (N1, N2 = 100) | Qbnb: 52 -> 54 | Helped |
| Use globally optimal Möbius Search instead of brute-force search | Conformal alignment of Disgust 01–Disgust 02 · Disgust 01–Disgust 02 (N1, N2 = 100) | Qbnb: 71 -> 75 | Helped |
| Use globally optimal Möbius Search instead of brute-force search | Conformal alignment of Happy 01–Happy 04 · Happy 01–Happy 04 (N1, N2 = 100) | Qbnb: 34 -> 53 | Helped |
| Use globally optimal Möbius Search instead of brute-force search | Conformal alignment of Sad 01–Sad 02 · Sad 01–Sad 02 (N1, N2 = 100) | Qbnb: 42 -> 45 | Helped |
| Use branch-and-bound search with closed-form rotation optimization rather than local ICP | Möbius alignment of conformally flattened surfaces · Synthetic data with 50% outliers | Qbnb | Helped |
| Use Möbius Search rather than ICP without a good initialization | Conformal alignment of the tested teeth and faces · Teeth and face alignment | Qtruth | Helped |
| Use Möbius Search rather than ICP with a good initialization | Synthetic Möbius alignment · Synthetic data with increasing outlier rate | Qbnb | Helped |
| Use Möbius Search rather than brute-force enumeration | Conformal alignment of the tested teeth and faces · Teeth and face alignment | runtime | Helped |
| Use Möbius Search rather than Möbius voting | Conformal alignment of the tested faces · Face alignment | Qtruth | Mixed |
| Reduce the input point count to 20 | Möbius alignment methods · Teeth alignment | Qtruth | Hurt |
Closest papers by meaning
- Wormhole Loss for Partial Shape Matching (NeurIPS 2024 · similarity 0.81)
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.81)
- Flow Matching on General Geometries (ICLR 2024 · similarity 0.81)
- SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency (CVPR 2024 · similarity 0.81)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.80)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.80)
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.