AI Paper Atlas

Research map / 3D vision / Face and shape

3D Shape Reconstruction from Vision and Touch

Edward Smith, Roberto Calandra, Adriana Romero, Georgia Gkioxari, David Meger, Jitendra Malik, Michal Drozdzal

NeurIPS 2020 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 29 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
replace sphere-based fusion with chart-based fusion (ablation)vision+touch model · validation, unoccluded visionavg Chamfer distance: 0.813 -> 0.751Improved
replace sphere-based fusion with chart-based fusion (ablation)vision+touch model · validation, occluded visionavg Chamfer distance: 0.992 -> 0.876Improved
replace sphere-based with chart-based (ablation)vision-only model · validation, occluded visionavg Chamfer distance: 1.072 -> 1.020Improved
add hard copying of touch charts to final prediction (ablation)chart-based model · validation, unoccluded visionavg Chamfer distance: 0.756 -> 0.751Improved
add hard copying of touch charts to final prediction (ablation)chart-based model · validation, occluded visionavg Chamfer distance: 0.919 -> 0.876Improved
add communication between touch and vision charts (ablation)chart-based model · validation, unoccluded visionavg Chamfer distance: 0.788 -> 0.751Improved
add communication between touch and vision charts (ablation)chart-based model · validation, occluded visionavg Chamfer distance: 1.014 -> 0.876Improved
add touch to occluded vision (ablation)chart-based model · validation, occluded visionavg Chamfer distance: 1.020 -> 0.876Improved
add touch to unoccluded vision (ablation)chart-based model · validation, unoccluded visionavg Chamfer distance: 0.797 -> 0.751Improved
remove vision (touch only) (ablation)chart-based model · test setglobal Chamfer distance: 1.074 -> 3.050Hurt
increase number of grasps from 1 to 5 (ablation)unoccluded vision + touch · multi-graspChamfer distance: 0.804 -> 0.654Improved
increase number of grasps from 1 to 5 (ablation)touch only · multi-graspChamfer distance: 3.05 -> 1.237Improved

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.

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