Research map / 3D vision / Face and shape
Deep Non-Rigid Structure From Motion With Missing Data
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 4-by-2 block sparse model to solve translation explicitly | Deep NRSfM · CMU MoCap subject 23 | normalized mean 3D error: 0.054 -> 0.060 | No clear effect |
| replace soft-thresholding with ReLU (ablation) | Deep NRSfM · appendix comparison | normalized mean 3D error | No clear effect |
| add hierarchical layers beyond single-layer sparse coding | Deep NRSfM · IKEA Average | normalized mean 3D error: 0.117 -> 0.010 | Improved |
| handle missing points via masked first layer instead of matrix completion | Deep NRSfM · PASCAL3D+ aeroplane orthogonal missing | normalized mean 3D error: 0.533 -> 0.033 | Improved |
| increase missing points up to 7 of 31 (ablation) | Deep NRSfM · CMU MoCap subject 23 | normalized mean 3D error: 0.604 | Hurt |
| add up to 20% Gaussian noise to 2D coordinates (ablation) | Deep NRSfM · CMU MoCap subject 70 | normalized mean 3D error | Hurt |
| add random scale and translation (weak perspective) | Deep NRSfM · PASCAL3D+ aeroplane complete no noise | normalized mean 3D error: 0.013 -> 0.034 | Hurt |
Closest papers by meaning
- Deep Non-Rigid Structure From Motion (ICCV 2019 · similarity 0.94)
- Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints (ECCV 2020 · similarity 0.94)
- Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling (AAAI 2025 · similarity 0.93)
- Deep Non-Rigid Structure-From-Motion: A Sequence-to-Sequence Translation Perspective (TPAMI 2024 · similarity 0.92)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.88)
- Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling (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.
