Research map / Graph learning / Graph algorithms and clustering
Simplicial Complex based Point Correspondence between Images warped onto Manifolds
Charu Sharma, Manohar Kaul
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 |
|---|---|---|---|
| match on the curved manifold directly instead of the unwrapped flat image | OurWarped · Chessboard | matching error (%): 3.64 -> 3.89 | Mixed |
| match on curved manifold rather than unwrapped equirectangular image | FGM · Chessboard | matching error (%): 84.0 -> 80.0 | Improved |
| use spherical (geodesic) matching rather than planar graph matching on unwrapped images | Tensor · Table | matching error (%): 72.4 -> 85.1 | Hurt |
| replace sphere with cone manifold (ablation) | OurWarped · Desktop spherical vs planar | matching error (%): 15.16 -> 14.71 | Mixed |
| replace sphere with ellipsoid manifold (ablation) | OurWarped · Table spherical vs planar | matching error (%): 0.78 -> 2.65 | Hurt |
| add RANSAC geometric verification to ORB | ORB · Desktop | matching error (%): 51.7 -> 29.3 | Improved |
| add RANSAC geometric verification to SPHORB | SPHORB · Desktop | matching error (%): 91.1 -> 96.1 | Hurt |
| rectify spherical images before BRISK | BRISK · Desktop | matching error (%): 78.9 -> 52.11 | Improved |
| use planar variant with Euclidean neighborhood versus Tensor | OurPlanar · Building | matching error (%): 43.24 -> 1.03 | Improved |
| apply random rotation, reflection, scaling and shear to 40-80% of landmarks (ablation) | OurWarped · Desktop | matching error (%) | No clear effect |
| add noise model II to input complex (ablation) | OurMethod · Chessboard | matching error (%): 4.17 -> 4.36 | Hurt |
Closest papers by meaning
- HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching (ICCV 2019 · similarity 0.87)
- Fast Globally Optimal and Geometrically Consistent 3D Shape Matching (ICCV 2025 · similarity 0.86)
- A Numerical Framework for Elastic Surface Matching, Comparison, and Interpolation (IJCV 2021 · similarity 0.86)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.85)
- Multi-Shape Matching with Cycle Consistency Basis via Functional Maps (AAAI 2025 · similarity 0.84)
- Partial-to-Partial Shape Matching with Geometric Consistency (CVPR 2024 · 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.
