Research map / 3D vision / Face and shape
4D Atlas: Statistical Analysis of the Spatiotemporal Variability in Longitudinal 3D Shape Data
Hamid Laga, Marcel Padilla, Ian H. Jermyn, Sebastian Kurtek, Mohammed Bennamoun, Anuj Srivastava
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 |
|---|---|---|---|
| register surfaces in SRNF space instead of functional-map methods (MapTree) | spatial registration · COMA | mean registration error: 1.6042 -> 0.0012 | Improved |
| register surfaces in SRNF space instead of MapTree | spatial registration · CAPE | mean registration error: 1.4447 -> 0.0008 | Improved |
| register surfaces in SRNF space instead of MapTree | spatial registration · DFAUST | mean registration error: 1.5344 -> 0.0008 | Improved |
| add the SRNF representation before PCA (ablation) | PCA on surfaces · DFAUST | mean reconstruction error: 0.26 -> 0.12 | Improved |
| add the SRNF representation before PCA (ablation) | PCA on surfaces · VOCA | mean reconstruction error: 0.030 -> 0.009 | Improved |
| add the SRNF representation before PCA (ablation) | PCA on surfaces · CAPE | mean reconstruction error: 0.105 -> 0.053 | Improved |
| add the TSRVF representation before PCA on 4D surfaces (ablation) | PCA on curves · DFAUST | mean reconstruction error: 0.926 -> 0.756 | Improved |
| add the TSRVF representation before PCA on 4D surfaces (ablation) | PCA on curves · VOCA | mean reconstruction error: 0.676 -> 0.486 | Improved |
| compute the mean in SRNF space rather than L2 in original surface space (ablation) | 4D/3D mean · DFAUST human bodies | mean shape quality (qualitative) | Improved |
| add temporal registration before averaging 4D surfaces (ablation) | 4D mean · DFAUST (qualitative) | mean 4D surface synchronization | Improved |
| add temporal registration (TSRVF) to unregistered 4D faces | 4D registration · VOCA with random time warps | distance between 4D surfaces | Improved |
Closest papers by meaning
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.93)
- A Riemannian Approach for Spatiotemporal Analysis and Generation of 4D Tree-shaped Structures (ECCV 2024 · similarity 0.92)
- A Riemannian Framework for the Elastic Analysis of the Spatiotemporal Variability in the Shape and Structure of Tree-Like 4D Objects (TPAMI 2026 · similarity 0.91)
- Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation (CVPR 2024 · similarity 0.86)
- Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models (NeurIPS 2025 · similarity 0.85)
- Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling (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.
