AI Paper Atlas

Research map / 3D vision / Face and shape

Active 3D Shape Reconstruction from Vision and Touch

Edward J. Smith, David Meger, Luis Pineda, Roberto Calandra, Jitendra Malik, Adriana Romero, Michal Drozdzal

NeurIPS 2021 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 2 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 the proposed reconstruction model instead of the cited T_G modelT_G reconstruction · T_G, 0 graspsChamfer distance: 25.586 -> 24.864Improved
Use the proposed reconstruction model instead of the cited T_G modelT_G reconstruction · T_G, 1 graspChamfer distance: 9.016 -> 8.220Improved
Use the proposed reconstruction model instead of the cited V&T_G modelV&T_G reconstruction · V&T_G, 0 graspsChamfer distance: 2.653 -> 2.538Improved
Use the proposed reconstruction model instead of the cited V&T_G modelV&T_G reconstruction · V&T_G, 1 graspChamfer distance: 2.637 -> 2.486Improved
Select a dataset-wide fixed trajectory by lowest average error rather than choose actions randomlyActive touch policy · T_P, 5 actionsCD ratio after 5 actions / initial CD: 36.38 -> 29.85Improved
Select a dataset-wide fixed trajectory by lowest average error rather than choose actions randomlyActive touch policy · T_G, 5 actionsCD ratio after 5 actions / initial CD: 25.83 -> 23.04Improved
Use nearest-neighbor action selection rather than random actionsActive touch policy · V&T_P, 5 actionsCD ratio after 5 actions / initial CD: 94.56 -> 91.79Improved
Use nearest-neighbor action selection rather than random actionsActive touch policy · V&T_G, 5 actionsCD ratio after 5 actions / initial CD: 90.65 -> 88.53Improved
Choose the fixed trajectory by lowest average error rather than most common best actionDataset-specific active touch policy · T_P, 5 actionsCD ratio after 5 actions / initial CD: 32.40 -> 29.85Improved
Choose the fixed trajectory by lowest average error rather than most common best actionDataset-specific active touch policy · T_G, 5 actionsCD ratio after 5 actions / initial CD: 23.46 -> 23.04Improved
Choose the fixed trajectory by lowest average error rather than most common best actionDataset-specific active touch policy · V&T_P, 5 actionsCD ratio after 5 actions / initial CD: 93.59 -> 92.36Improved
Choose the fixed trajectory by lowest average error rather than most common best actionDataset-specific active touch policy · V&T_G, 5 actionsCD ratio after 5 actions / initial CD: 89.39 -> 89.31No clear effect

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