Research map / 3D vision / Human pose estimation
Unsupervised Pose-Aware Part Decomposition for Man-Made Articulated Objects
Yuki Kawana, Yusuke Mukuta, Tatsuya Harada
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 category-common shape decoder (ablation) | PPD · Articulated objects ablation, mean over 5 categories | label IoU: 55.67 -> 80.99 | Improved |
| add category-common shape decoder (ablation) | PPD · Articulated objects ablation, mean over 5 categories | EPE: 8.827 -> 2.988 | Improved |
| add category-common pose decoder (ablation) | PPD · Articulated objects ablation, mean over 5 categories | label IoU: 71.35 -> 80.99 | Improved |
| add category-common pose decoder (ablation) | PPD · Articulated objects ablation, mean over 5 categories | EPE: 7.219 -> 2.988 | Improved |
| add variance loss L_var (ablation) | PPD · Articulated objects ablation, mean over 5 categories | label IoU: 65.29 -> 80.99 | Improved |
| add volume loss L_vol (ablation) | PPD · Articulated objects ablation, mean over 5 categories | label IoU: 72.20 -> 80.99 | Improved |
| add deviation loss L_dev (ablation) | PPD · Articulated objects ablation, mean over 5 categories | EPE: 6.628 -> 2.988 | Improved |
| add location loss L_loc (ablation) | PPD · Articulated objects ablation, mean over 5 categories | EPE: 9.250 -> 2.988 | Improved |
| add adversarial loss (ablation) | PPD · Articulated objects ablation, mean over 5 categories | label IoU: 70.14 -> 80.99 | Improved |
| PPD instead of BSP-Net for part segmentation | BSP-Net · Articulated objects, part segmentation (canonical-pose labeling), mean | label IoU: 76.65 -> 80.99 | Improved |
| PPD instead of BAE-Net for part segmentation | BAE-Net · Articulated objects, part segmentation (canonical-pose labeling), mean | label IoU: 39.17 -> 80.99 | Improved |
| use depth map input instead of complete point cloud | PPD · Depth map vs complete point cloud | label IoU: 80.99 -> 80.65 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BSP-Net — BSP-Net: Generating Compact Meshes via Binary Space Partitioning (CVPR 2020) · better on 5 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis (NeurIPS 2024 · similarity 0.91)
- Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image (NeurIPS 2023 · similarity 0.90)
- CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image (CVPR 2025 · similarity 0.87)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.87)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.87)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.87)
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.
