Research map / 3D vision / Face and shape
"Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction From Multiple Perspective Views
Pan Ji, Hongdong Li, Yuchao Dai, Ian Reid
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 the convex rigidity SDP instead of the best perspective NRSfM baseline | Convex rigidity SDP · Flag dataset (semi-synthetic NRSfM) | 3D RMSE (mm): 21.08 -> 16.75 | Improved |
| use the convex rigidity SDP instead of the best baseline, with incomplete data | Convex rigidity SDP · Jumping Trousers (NRSfM, missing data) | 3D RMSE (mm): 44.05 -> 37.70 | Improved |
| use the convex rigidity SDP on a point-articulated sequence | Convex rigidity SDP · Synthetic point-articulated | 3D RMSE (mm): 17.48 -> 7.70 | Improved |
| use the convex rigidity SDP on an axis-articulated sequence | Convex rigidity SDP · Synthetic axis-articulated | 3D RMSE (mm): 9.13 -> 3.07 | Improved |
| use the convex rigidity SDP instead of a rigid-specific method on rigid data | Convex rigidity SDP · Model House (rigid SfM) | 3D RMSE: 0.158 vs 0.162 | Mixed |
| use the convex rigidity SDP instead of the NRSfM baseline on rigid data | Convex rigidity SDP · Model House (rigid SfM) | 3D RMSE: 0.200 -> 0.162 | Improved |
| use perspective-camera methods instead of orthographic-camera methods | Convex rigidity SDP · Flag dataset (semi-synthetic NRSfM) | 3D RMSE (mm): 41.92 -> 21.08 | Improved |
Closest papers by meaning
- Inextensible Non-Rigid Shape-From-Motion by Second-Order Cone Programming (CVPR 2016 · similarity 0.92)
- Inextensible Non-Rigid Structure-from-Motion by Second-Order Cone Programming (TPAMI 2017 · similarity 0.92)
- PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-Rigid Structure-From-Motion (ICCV 2021 · similarity 0.89)
- Incremental Non-Rigid Structure-from-Motion with Unknown Focal Length (ECCV 2018 · similarity 0.89)
- A Benchmark and Evaluation of Non-Rigid Structure from Motion (IJCV 2020 · similarity 0.88)
- Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling (CVPR 2024 · similarity 0.86)
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.
