AI Paper Atlas

Research map / 3D vision / Human pose estimation

Towards Accurate Alignment in Real-Time 3D Hand-Mesh Reconstruction

Xiao Tang, Tianyu Wang, Chi-Wing Fu

ICCV 2021 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 82 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 joint stage (ablation)mesh+refine pipeline · FreiHAND train-split validation (ablation, hand-level alignment)mIoU: 92.42 -> 92.95Improved
add refine stage (ablation)joint+mesh pipeline · FreiHAND train-split validation (ablation, hand-level alignment)mIoU: 92.05 -> 92.95Improved
add refine stage (ablation)joint+mesh pipeline · FreiHAND train-split validation (ablation, hand-level alignment)HD: 5.93 -> 4.70Improved
add local projection unit (ablation)refine stage · FreiHAND train-split validation (ablation, hand-level alignment)mIoU: 92.55 -> 92.95Improved
add global broadcast unit (ablation)refine stage · FreiHAND train-split validation (ablation, hand-level alignment)mIoU: 92.63 -> 92.95Improved
regress per-vertex offsets instead of direct vertex coordinates (ablation)refine stage Graph-CNN · FreiHAND train-split validation (ablation, hand-level alignment)mIoU: 88.01 -> 92.95Improved
regress per-vertex offsets instead of direct vertex coordinates (ablation)refine stage Graph-CNN · FreiHAND train-split validation (ablation, hand-level alignment)Mesh AUC: 0.782 -> 0.866Improved
add segmentation branch and silhouette loss (ablation)full method · FreiHAND train-split validation (ablation, hand-level alignment)mIoU: 92.50 -> 92.95Improved
add render loss (ablation)full method · FreiHAND train-split validation (ablation, hand-level alignment)mIoU: 92.80 -> 92.95Improved
add render loss (ablation)full method · FreiHAND train-split validation (ablation, hand-level alignment)HD: 4.97 -> 4.70Improved
add ObMan synthetic data to trainingfull method · FreiHAND testME (10mm): 0.71 -> 0.67Improved
replace I2L-MeshNet with decoupled three-stage method3D hand mesh reconstruction · FreiHAND finger-level alignmentmIoU: 71.07 -> 77.33Improved

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