Research map / 3D vision / Face and shape
Basis Restricted Elastic Shape Analysis on the Space of Unregistered Surfaces
Emmanuel Hartman, Emery Pierson, Martin Bauer, Mohamed Daoudi, Nicolas Charon
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 |
|---|---|---|---|
| use varifold distance instead of Chamfer for shape matching (ablation) | BaRe-ESA · FAUST registration | registration error: 0.032 -> 0.014 | Improved |
| use varifold distance instead of Chamfer for shape matching (ablation) | BaRe-ESA · DFAUST interpolation | Hausdorff: 1.273 -> 1.072 | Improved |
| use elastic H2 path energy instead of Euclidean latent distance (ablation) | BaRe-ESA · DFAUST interpolation | Hausdorff: 1.787 -> 1.072 | Improved |
| use elastic H2 path energy instead of Euclidean latent distance (ablation) | BaRe-ESA · DFAUST interpolation | Varifold: 0.335 -> 0.290 | Improved |
| use elastic H2 path energy instead of Euclidean latent distance (ablation) | BaRe-ESA · FAUST registration | registration error: 0.015 -> 0.014 | No clear effect |
| train basis on 4D data instead of 3D-only elastic geodesics (ablation) | BaRe-ESA · DFAUST interpolation | Hausdorff: 2.004 -> 1.072 | Improved |
| train basis on 4D data instead of 3D-only elastic geodesics (ablation) | BaRe-ESA · DFAUST interpolation | Varifold: 0.405 -> 0.290 | Improved |
| increase shape basis from 10 to 40 vectors at 130 pose vectors (ablation) | BaRe-ESA · FAUST registration | registration error: 0.016 -> 0.014 | Improved |
| increase pose basis from 10 to 130 vectors (ablation) | BaRe-ESA · FAUST registration | registration error: 0.090 -> 0.016 | Improved |
| increase pose basis from 130 to 190 vectors (ablation) | BaRe-ESA · FAUST registration | registration error: 0.014 -> 0.015 | No clear effect |
| BaRe-ESA vs 3D-Coded | BaRe-ESA · FaustE registration | MSE: 0.053 -> 0.014 | Improved |
| BaRe-ESA vs ARAPReg | BaRe-ESA · DFAUST extrapolation | Hausdorff: 5.004 -> 2.592 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- 3D-Coded — 3D-CODED: 3D Correspondences by Deep Deformation (ECCV 2018) · better on 7 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes (ICCV 2023 · similarity 0.91)
- Elastic Shape Analysis of Surfaces with Second-Order Sobolev Metrics: A Comprehensive Numerical Framework (IJCV 2023 · similarity 0.90)
- Numerical Inversion of SRNF Maps for Elastic Shape Analysis of Genus-Zero Surfaces (TPAMI 2017 · similarity 0.89)
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.88)
- Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction (ICLR 2024 · similarity 0.86)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 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.
