Research map / 3D vision / Face and shape
Online Unsupervised Learning of the 3D Kinematic Structure of Arbitrary Rigid Bodies
Urbano Miguel Nunes, Yiannis Demiris
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 |
|---|---|---|---|
| build similarity from accumulated variation of pairwise distance (AVPED) with embedding instead of standard-deviation similarity of Perera and Barnes (ablation) | online kinematic structure learning · six RGB-D sequences (donkey, lamp, pipe 1/2, pipe 3/4, iCub, iCub arm) | precision, recall, f-measure | Improved |
| use online AVPED method instead of offline subspace clustering | 3D motion segmentation of Nunes and Demiris · six RGB-D sequences | precision, recall, f-measure | No clear effect |
| reduce number of sub-sampled points tracked (ablation) | proposed method · six RGB-D sequences | number of segments estimated | No clear effect |
| incorporate the spectrum transformation (keep l leading eigenvalues) into the distance matrix to handle noise (ablation) | proposed method · noise eigenvalue spectrum | negative eigenvalue magnitude | Improved |
Closest papers by meaning
- Highly Articulated Kinematic Structure Estimation Combining Motion and Skeleton Information (TPAMI 2017 · similarity 0.89)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.88)
- Unsupervised 3D Reconstruction and Grouping of Rigid and Non-Rigid Categories (TPAMI 2020 · similarity 0.88)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.87)
- Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video (NeurIPS 2026 · similarity 0.86)
- Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis (NeurIPS 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.
