Research map / 3D vision / 3D generation
VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects
Ruihai Wu, Yan Zhao, Kaichun Mo, Zizheng Guo, Yian Wang, Tianhao Wu, Qingnan Fan, Xuelin Chen, Leonidas Guibas, Hao Dong
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 |
|---|---|---|---|
| use task-conditioned dense affordances and trajectory proposals instead of the heuristic planner | VAT-Mart · Door pushing | success rate (%): 25.74 -> 55.14 | Improved |
| use task-conditioned dense affordances and trajectory proposals instead of the heuristic planner | VAT-Mart · Door pulling | success rate (%): 8.82 -> 12.04 | Improved |
| use task-conditioned dense affordances and trajectory proposals instead of the heuristic planner | VAT-Mart · Drawer pushing | success rate (%): 40.25 -> 56.02 | Improved |
| use task-conditioned dense affordances and trajectory proposals instead of the heuristic planner | VAT-Mart · Drawer pulling | success rate (%): 25.02 -> 43.53 | Improved |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Door pushing | F-score (%): 77.55 / 70.80 -> 82.76 / 72.54 | Improved |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Door pulling | F-score (%): 72.62 / 69.94 -> 76.06 / 72.01 | Improved |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Drawer pushing | F-score (%): 75.45 / 64.89 -> 81.65 / 70.52 | Improved |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Drawer pulling | F-score (%): 68.89 / 66.47 -> 80.23 / 71.71 | Improved |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Door pushing | Coverage (%): 82.35 / 75.52 -> 82.00 / 70.54 | Mixed |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Door pulling | Coverage (%): 50.17 / 43.52 -> 58.68 / 48.29 | Improved |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Drawer pushing | Coverage (%): 63.25 / 60.08 -> 74.15 / 68.08 | Improved |
| add curiosity feedback to exploration (ablation) | VAT-Mart visual priors · Drawer pulling | Coverage (%): 62.56 / 49.43 -> 81.15 / 64.31 | Improved |
Later papers that compared with this method
1 later accepted paper reports VAT-MART as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding (ICCV 2025 · better on 2 of 2 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
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.88)
- GMAP: Generalized Manipulation of Articulated Objects in Robotic Using Pre-trained Model (AAAI 2025 · similarity 0.87)
- AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning (ICLR 2025 · similarity 0.87)
- VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation (CVPR 2025 · similarity 0.87)
- OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints (CVPR 2025 · similarity 0.87)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · 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.
