Research map / 3D vision / Depth and stereo
Prior-Less Compressible Structure From Motion
Chen Kong, Simon Lucey
Check 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 block-sparse compressible SfM instead of low-rank SfM | Prior-Less Compressible SfM vs. Dai et al. · Synthetic structures with rank 3L, L=3 to 12 | structure reconstruction error | Improved |
| Use block-sparse compressible SfM instead of low-rank SfM | Prior-Less Compressible SfM vs. Dai et al. · Synthetic low-rank structures | structure reconstruction error | Improved |
| Use block-sparse compressible SfM instead of low-rank SfM | Prior-Less Compressible SfM vs. Dai et al. · Synthetic low-rank structures with varying noise ratios | camera matrix error | Mixed |
| Use block-sparse compressible SfM instead of low-rank SfM | Prior-Less Compressible SfM vs. Dai et al. · Synthetic low-rank structures with varying noise ratios | structure reconstruction error | Mixed |
| Apply compressible SfM to real sequences with sufficiently coherent learned dictionaries | Prior-Less Compressible SfM · CMU Motion Capture sequences | 3D structure reconstruction | Improved |
| Apply compressible SfM to the Shark sequence despite poor dictionary coherence | Prior-Less Compressible SfM · Shark sequence | 3D structure reconstruction | Hurt |
| Decrease dictionary size L and sparsity level K (ablation) | Learned dictionary for Motion-4 by Subject-5 · CMU Motion Capture Motion-4, Subject-5 | dictionary coherence | Improved |
| Decrease dictionary size L and sparsity level K (ablation) | Learned dictionary for Motion-4 by Subject-5 · CMU Motion Capture Motion-4, Subject-5 | approximation error | Hurt |
| Increase noise ratio (ablation) | Prior-Less Compressible SfM · Synthetic low-rank structures, L=5 | camera matrix error | Hurt |
| Increase noise ratio (ablation) | Prior-Less Compressible SfM · Synthetic low-rank structures, L=5 | structure reconstruction error | Hurt |
Closest papers by meaning
- Self-Expressive Dictionary Learning for Dynamic 3D Reconstruction (TPAMI 2017 · similarity 0.89)
- Deep Non-Rigid Structure From Motion (ICCV 2019 · similarity 0.88)
- MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025 · similarity 0.87)
- Organic Priors in Non-rigid Structure from Motion (ECCV 2022 · similarity 0.87)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.86)
- Light3R-SfM: Towards Feed-forward 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.
