AI Paper Atlas

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

ICLR 2022 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 25 citations (OpenAlex)

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 changedWhereMeasuredEffect
use task-conditioned dense affordances and trajectory proposals instead of the heuristic plannerVAT-Mart · Door pushingsuccess rate (%): 25.74 -> 55.14Improved
use task-conditioned dense affordances and trajectory proposals instead of the heuristic plannerVAT-Mart · Door pullingsuccess rate (%): 8.82 -> 12.04Improved
use task-conditioned dense affordances and trajectory proposals instead of the heuristic plannerVAT-Mart · Drawer pushingsuccess rate (%): 40.25 -> 56.02Improved
use task-conditioned dense affordances and trajectory proposals instead of the heuristic plannerVAT-Mart · Drawer pullingsuccess rate (%): 25.02 -> 43.53Improved
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Door pushingF-score (%): 77.55 / 70.80 -> 82.76 / 72.54Improved
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Door pullingF-score (%): 72.62 / 69.94 -> 76.06 / 72.01Improved
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Drawer pushingF-score (%): 75.45 / 64.89 -> 81.65 / 70.52Improved
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Drawer pullingF-score (%): 68.89 / 66.47 -> 80.23 / 71.71Improved
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Door pushingCoverage (%): 82.35 / 75.52 -> 82.00 / 70.54Mixed
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Door pullingCoverage (%): 50.17 / 43.52 -> 58.68 / 48.29Improved
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Drawer pushingCoverage (%): 63.25 / 60.08 -> 74.15 / 68.08Improved
add curiosity feedback to exploration (ablation)VAT-Mart visual priors · Drawer pullingCoverage (%): 62.56 / 49.43 -> 81.15 / 64.31Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy