AI Paper Atlas

Research map / 3D vision / Human pose estimation

RenderIH: A Large-Scale Synthetic Dataset for 3D Interacting Hand Pose Estimation

Lijun Li, Linrui Tian, Xindi Zhang, Qi Wang, Bang Zhang, Liefeng Bo, Mengyuan Liu, Chen Chen

ICCV 2023 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 27 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 RenderIH synthetic data to IH2.6M trainingIntagHand · IH2.6M testMPJPE (mm): 10.9 -> 9.72Improved
add RenderIH synthetic data to IH2.6M trainingInterNet · IH2.6M testMPJPE (mm): 18.28 -> 17.19Improved
add RenderIH synthetic data to IH2.6M trainingTransHand · IH2.6M testMPJPE (mm): 10.6 -> 10.06Improved
pretrain on RenderIH then finetune on IH2.6MTransHand · IH2.6M testPAMPJPE (mm): 6.76 -> 5.79Improved
pretrain on synthetic then finetune rather than mixing datasetsTransHand · IH2.6M testMPJPEImproved
add correlation encoder fusing other-hand features (ablation)TransHand · IH2.6M testPAMPJPE (mm): 7.32 -> 6.76Improved
add natural discriminator to pose optimization (ablation)RenderIH pose generation · user studynatural rate: 54.68% -> 81.25%Improved
train on RenderIH instead of H2O-3D or Ego3d (40K samples each)TransHand · TzionasMPJPE (mm): 35.61 -> 32.80 (vs H2O-3D)Improved
increase synthetic data beyond about 900K imagesTransHand · IH2.6M testMPJPENo clear effect
finetune RenderIH-pretrained model on only 1% real data (ablation)TransHand · IH2.6M testMPJPE (mm): 27.73 -> 12.6Improved
train on RenderIH only instead of IH2.6MTransHand · TzionasMPJPE (mm): 11.38 -> 22.11Hurt
use anchors instead of all vertices for hand attractionRenderIH pose optimization · qualitativepose qualityNo 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