Research map / 3D vision / Face and shape
Symmetric Non-rigid Structure from Motion for Category-Specific Object Structure Estimation
Yuan Gao, Alan L. Yuille
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 |
|---|---|---|---|
| add symmetry constraint | EM-PPCA · Pascal3D+ bus | mean rotation error: 0.26 -> 0.21 | Improved |
| add symmetry constraint | EM-PPCA · Pascal3D+ car | mean rotation error: 0.39 -> 0.34 | Improved |
| add symmetry constraint | EM-PPCA · Pascal3D+ sofa | mean rotation error: 0.79 -> 0.34 | Improved |
| add symmetry constraint | EM-PPCA · Pascal3D+ aeroplane | mean rotation error: 0.34 -> 0.31 | Improved |
| add symmetry constraint | EM-PPCA · Pascal3D+ tv | mean rotation error: 0.41 -> 0.52 | Hurt |
| add symmetry constraint | PriorFree · Pascal3D+ aeroplane | mean rotation error: 0.52 -> 0.46 | Improved |
| add symmetry constraint | PriorFree · Pascal3D+ bus | mean rotation error: 0.47 -> 1.23 | Hurt |
| add symmetry constraint | PriorFree · Pascal3D+ car | mean rotation error: 0.86 -> 0.79 | Improved |
| add symmetry constraint | PriorFree · Pascal3D+ sofa | mean rotation error: 1.36 -> 0.85 | Improved |
| add symmetry constraint | EM-PPCA · Pascal3D+ aeroplane subtype I | mean shape error: 0.36 -> 0.33 | Improved |
| increase keypoint noise from 0.03 to 0.07 d_max | Sym-EM-PPCA · Pascal3D+ aeroplane (noisy keypoints) | mean rotation error: 0.32 -> 0.35 | Hurt |
| add symmetry constraint under noise sigma=0.07 d_max | EM-PPCA · Pascal3D+ aeroplane (noisy keypoints) | mean rotation error: 0.36 -> 0.35 | Improved |
Closest papers by meaning
- Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation From Single and Multiple Images (CVPR 2017 · similarity 0.93)
- Modelling and unsupervised learning of symmetric deformable object categories (NeurIPS 2018 · similarity 0.90)
- Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories (CVPR 2018 · similarity 0.89)
- Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild (CVPR 2020 · 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.
