Research map / 3D vision / Face and shape
Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MUS multiple-union-of-subspaces reconstruction and clustering instead of competing SfM/NRSfM methods | Synthetic rigid-category collections · Eight PASCAL VOC categories, noise-free annotations | eX: 0.361 -> 0.186 | Helped |
| Use MUS multiple-union-of-subspaces reconstruction and clustering instead of competing SfM/NRSfM methods | Synthetic rigid-category collections · Eight PASCAL VOC categories, noisy annotations | eX: 0.363 -> 0.196 | Helped |
| Estimate object clusters jointly with reconstruction using MUS rather than LRR from 2D annotations | Synthetic rigid-category collections · Eight PASCAL VOC categories, noise-free annotations | aC: 0.40 -> 0.88 | Helped |
| Estimate object clusters jointly with reconstruction using MUS rather than LRR from 2D annotations | Synthetic rigid-category collections · Eight PASCAL VOC categories, noisy annotations | aC: 0.40 -> 0.89 | Helped |
| Jointly infer object identity and deformation type from partial annotations | MUS · ASL collection | aC: aC = 1.0(2) | Helped |
Closest papers by meaning
- Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction (NeurIPS 2020 · similarity 0.88)
- Jumping Manifolds: Geometry Aware Dense Non-Rigid Structure From Motion (CVPR 2019 · similarity 0.88)
- DUST: Dual Union of Spatio-Temporal Subspaces for Monocular Multiple Object 3D Reconstruction (CVPR 2017 · similarity 0.87)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.87)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.86)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (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.