atlas

Research map / 3D vision / Human pose estimation

Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural Rendering

CVPR 2019 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 220 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use the full dense hand mesh estimator instead of the compared segmentation methodsHand segmentation · RHDIoU scoreHelped
Add iterative testing refinement (ablation)DHPE · DO3D pose estimation accuracyHelped
Add iterative testing refinement (ablation)DHPE · RHD3D pose estimation accuracyNo clear effect
Add self-supervised data augmentation using fitted meshes (ablation)DHPE · RHD and DO3D pose estimation accuracyHelped
Add 2D evidence losses for joint and feature supervision (ablation)DHPE · RHD and DO3D pose estimation accuracyHelped
Schedule the shape-loss weight based on articulation error instead of keeping it constant (ablation)DHPE training · RHD and DOtest errorHelped
Jointly estimate hand shape and pose rather than estimating pose alone (ablation)DHPE · RHD3D pose estimation accuracyHelped
Use both 2D features and 2D skeletons as inputs to iterative mesh estimation (ablation)DHPE · RHD and DO3D pose estimation accuracyHelped
Add a 2D pose refiner trained with auxiliary 2D joint supervision (ablation)DHPE · RHD and DO3D pose estimation accuracyHelped

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