AI Paper Atlas

Research map / 3D vision / 3D generation

AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction

Zerui Chen, Yana Hasson, Cordelia Schmid, Ivan Laptev

ECCV 2022 · 3D vision › 3D generation · approach: Hand-object interaction generation · 73 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
add MANO-based pose normalization of query points for the hand SDF (model c vs a) (ablation)hand SDF decoder · ObMan hand-only (87K train)H_se: 0.128 -> 0.124Improved
add MANO-based pose normalization of query points for the hand SDF (model c vs a) (ablation)hand SDF decoder · ObMan hand-only (30K train)H_se: 0.183 -> 0.168Improved
add MANO network jointly trained with the SDF decoder (b vs a) (ablation)hand SDF decoder · ObMan hand-only (87K train)H_se: 0.128 -> 0.126Improved
add pose normalization on top of joint MANO training (c vs b) (ablation)hand SDF decoder · ObMan hand-only (87K train)H_je: 1.18 -> 1.20Hurt
use ground-truth hand pose instead of estimated pose (ablation)AlignSDF hand · ObMan hand-only (87K train)H_se: 0.124 -> 0.101Improved
add hand pose alignment to hand-object model (e vs d) (ablation)hand-object SDF · ObMan hand-object (87K train)H_se: 0.140 -> 0.131Improved
add hand pose alignment to hand-object model (e vs d) (ablation)hand-object SDF · ObMan hand-object (87K train)O_se: 4.09 -> 4.14Hurt
add object translation alignment to hand-object model (f vs d) (ablation)hand-object SDF · ObMan hand-object (87K train)O_se: 4.09 -> 3.36Improved
add object translation alignment alone (f vs d) (ablation)hand-object SDF · ObMan hand-object (87K train)H_se: 0.140 -> 0.148Hurt
combine hand and object alignment (g vs e) (ablation)hand-object SDF · ObMan hand-object (87K train)H_se: 0.131 -> 0.136Hurt
use ground-truth hand pose and object translation instead of estimates (g* vs g) (ablation)AlignSDF · ObMan hand-object (87K train)O_se: 3.38 -> 2.11Improved
replace Karunratanakul et al. 2De with AlignSDFhand-object reconstruction · ObManH_se: 0.237 -> 0.136Improved

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