Research map / 3D vision / Face and shape
Jumping Manifolds: Geometry Aware Dense Non-Rigid Structure From Motion
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 MoJu instead of SDG | Dense NRSfM · Face Sequence 1 | mean normalized 3D reconstruction error: 0.0443 -> 0.0404 | Helped |
| Use MoJu instead of SDG | Dense NRSfM · Face Sequence 2 | mean normalized 3D reconstruction error: 0.0381 -> 0.0392 | Hurt |
| Use MoJu instead of SDG | Dense NRSfM · Face Sequence 3 | mean normalized 3D reconstruction error: 0.0294 -> 0.0280 | Helped |
| Use MoJu instead of SDG | Dense NRSfM · Face Sequence 4 | mean normalized 3D reconstruction error: 0.0309 -> 0.0327 | Hurt |
| Use MoJu instead of SDG | Dense NRSfM · Actor Sequence 1 | mean normalized 3D reconstruction error: 0.0340 -> 0.0274 | Helped |
| Use MoJu instead of SMSR | Dense NRSfM · Actor Sequence 2 | mean normalized 3D reconstruction error: 0.0334 -> 0.0289 | Helped |
| Use MoJu instead of SDG | Dense NRSfM · Paper Sequence | mean normalized 3D reconstruction error: 0.0394 -> 0.0338 | Helped |
| Use MoJu instead of SDG | Dense NRSfM · T-shirt Sequence | mean normalized 3D reconstruction error: 0.0362 -> 0.0386 | Hurt |
| Add geometry-aware handling of noisy trajectories | MoJu · Synthetic Face dataset with Gaussian trajectory noise | mean normalized 3D reconstruction error | Helped |
| Vary the number of top singular vectors used for Grassmannian representation (ablation) | MoJu · Synthetic Face dataset | mean normalized 3D reconstruction error | No clear effect |
Closest papers by meaning
- Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian Perspective (CVPR 2018 · similarity 0.93)
- Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories (CVPR 2018 · similarity 0.88)
- Grassmann Manifold Flows for Stable Shape Generation (NeurIPS 2023 · similarity 0.87)
- Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space (CVPR 2017 · similarity 0.87)
- Geometric Analysis of Nonlinear Manifold Clustering (NeurIPS 2024 · 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.