AI Paper Atlas

Research map / 3D vision / Human pose estimation

S2Contact: Graph-Based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning

Tze Ho Elden Tse, Zhongqun Zhang, Kwang In Kim, Aleš Leonardis, Feng Zheng, Hyung Jin Chang

ECCV 2022 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 20 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 semi-supervised learning with pseudo-labels (ablation)S2Contact · HO-3Dhand joint error (mm): 9.92 -> 8.74Improved
add semi-supervised learning with pseudo-labels (ablation)S2Contact · HO-3Dobject ADD-0.1D (%): 72.81 -> 81.37Improved
add semi-supervised learning (cross-dataset) (ablation)S2Contact · DexYCBobject ADD-0.1D avg (%): 63.8 -> 70.5Improved
add contact consistency loss L_cont (ablation)S2Contact · HO-3Dobject ADD-0.1D (%): 75.92 -> 81.37Improved
add visual consistency filter L_SSIM (ablation)S2Contact · HO-3Dobject ADD-0.1D (%): 73.33 -> 81.37Improved
add visual consistency filter L_SSIM (ablation)S2Contact · HO-3Dhand joint error (mm): 9.71 -> 8.74Improved
add Chamfer geometric filter (ablation)S2Contact · HO-3Dcontact coverage (%): 13.1 -> 19.2Improved
add Chamfer geometric filter (ablation)S2Contact · HO-3Dhand joint error (mm): 8.53 -> 8.74Hurt
add SDF penetration filter (ablation)S2Contact · HO-3Dobject ADD-0.1D (%): 80.90 -> 81.37Improved
increase K neighbours from 5 to 10 (no dilation) (ablation)S2Contact · ContactPosehand joint error (mm): 8.252 -> 6.691Improved
increase K neighbours from 10 to 15 (ablation)S2Contact · ContactPosehand joint error (mm): 6.691 -> 6.715No clear effect
add dilation d=4 with K=10 instead of d=2 (ablation)GCN-Contact · HO-3D (w/o semi)hand joint error (mm): 10.91 -> 9.92Improved

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