Research map / 3D vision / Human pose estimation
SIAM: Towards Generalizable Articulated Object Modeling via Single Robot-Object Interaction
Yuyan Liu, Li Zhang, Di Wu, Yan Zhang, Anran Huang, Zhi Wang, Liu Liu, Dan Guo
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 |
|---|---|---|---|
| SIAM vs SAGCI part segmentation | SIAM · PartNet-Mobility Door (unseen) | AP50: 20.86 -> 89.47 | Improved |
| SIAM vs GAPartNet on Oven (unseen) | SIAM · PartNet-Mobility Oven (unseen) | AP50: 29.21 -> 33.7 | Mixed |
| SIAM vs EfficientCAPER joint angle error, Safe | SIAM · PartNet-Mobility Safe (seen) | Axis angle error (deg): 2.2 -> 2.1 | Improved |
| SIAM vs CARTO whole-shape CD, Door | SIAM · PartNet-Mobility Door (unseen) | Chamfer distance: 2.69 -> 1.62 | Improved |
| use learned slight interaction instead of random grasp (ablation) | SIAM · initial grasp ablation | AP50: 13.81 -> 86.47 | Improved |
| add geometric energy term to kinematic-only energy (ablation) | SIAM · revolute joint | Axis angle error (deg): 5.6 -> 4.0 | Improved |
| add kinematic energy term to geometric-only energy (ablation) | SIAM · revolute joint | Axis angle error (deg): 4.2 -> 4.0 | Improved |
| add flow-weighting EV and consistency EC within geometric energy (ablation) | SIAM · revolute joint | Axis angle error (deg): 4.8 -> 4.2 (w/o EV vs EG-only) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- EfficientCAPER — EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation (NeurIPS 2024) · better on 2 of 2 shared results
- U-COPE — U-COPE: Taking a Further Step to Universal 9D Category-level Object Pose Estimation (ECCV 2024) · better on 2 of 2 shared results
- CARTO — CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects (CVPR 2023) · better on 1 of 1 shared result
- A-SDF — A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation (ICCV 2021) · better on 1 of 1 shared result
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
- GMAP: Generalized Manipulation of Articulated Objects in Robotic Using Pre-trained Model (AAAI 2025 · similarity 0.89)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.88)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.87)
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model (ICLR 2025 · similarity 0.87)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.87)
- URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model (NeurIPS 2025 · 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.
