Research map / 3D vision / Face and shape
Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian Perspective
Read the paperCheck 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 the spatio-temporal Grassmannian method instead of DV | Dense NRSfM · Synthetic face sequences 1–4 | e3D: 0.0531 -> 0.0443; 0.0457 -> 0.0381; 0.0346 -> 0.0294; 0.0379 -> 0.0309 | Helped |
| Use the spatio-temporal Grassmannian method instead of DS | Dense NRSfM · kinect_paper and kinect_tshirt | e3D: 0.0612 -> 0.0394; 0.0636 -> 0.0362 | Helped |
| Add the spatial constraint to the formulation (ablation) | Proposed method · Synthetic face sequences | e3D | Helped |
| Add the temporal constraint to the formulation (ablation) | Proposed method · Synthetic face sequences | e3D | Helped |
| Use a small number of eigenvalues for each local structure instead of all eigenvalues (ablation) | Proposed method · Noise-free sequences | e3D | No clear effect |
| Increase the number of local subspaces beyond a certain value (ablation) | Proposed method · Noise-free sequences | e3D | No clear effect |
| Add Gaussian noise to the measurement matrix | Proposed method · Synthetic face and kinect sequences | e3D | No clear effect |
Closest papers by meaning
- Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling (AAAI 2025 · similarity 0.90)
- Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling (CVPR 2024 · similarity 0.89)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.86)
- Structure-from-Motion with a Non-Parametric Camera Model (CVPR 2025 · similarity 0.86)
- Dense-SfM: Structure from Motion with Dense Consistent Matching (CVPR 2025 · similarity 0.85)
- MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025 · 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.