Research map / 3D vision / Face and shape
Deep Non-Rigid Structure From Motion
Chen Kong, Simon Lucey
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 Deep NRSfM instead of the best prior method (RIKS) on IKEA | Deep NRSfM · IKEA | normalized mean 3D error: 0.117 -> 0.010 | Improved |
| use Deep NRSfM instead of the best prior method (RIKS) on PASCAL3D+ | Deep NRSfM · PASCAL3D+ original | normalized mean 3D error: 0.159 -> 0.014 | Improved |
| use Deep NRSfM on large-scale CMU MoCap versus CNS | Deep NRSfM · CMU MoCap seen motions | normalized mean 3D error: 0.577 -> 0.101 | Improved |
| add 20% Gaussian noise to 2D coordinates of subject 70 | Deep NRSfM · CMU MoCap subject 70 | normalized mean 3D error | Hurt |
| add noise perturbation to 2D annotations on PASCAL3D+ | Deep NRSfM · PASCAL3D+ average | normalized mean 3D error: 0.014 -> 0.017 | Hurt |
| test on unseen motions rather than training motions | Deep NRSfM · CMU MoCap average | normalized mean 3D error: 0.101 -> 0.287 | Hurt |
| lower final dictionary mutual coherence | Deep NRSfM · CMU MoCap training | 3D reconstruction error | Improved |
Closest papers by meaning
- Deep Non-Rigid Structure From Motion With Missing Data (TPAMI 2020 · similarity 0.94)
- Deep Non-Rigid Structure-From-Motion: A Sequence-to-Sequence Translation Perspective (TPAMI 2024 · similarity 0.92)
- Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints (ECCV 2020 · similarity 0.92)
- Procrustean Regression Networks: Learning 3D Structure of Non-Rigid Objects from 2D Annotations (ECCV 2020 · similarity 0.91)
- Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling (AAAI 2025 · similarity 0.90)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.87)
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.
