AI Paper Atlas

Research map / 3D vision / Human pose estimation

A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation From a Single Depth Image

Fu Xiong, Boshen Zhang, Yang Xiao, Zhiguo Cao, Taidong Yu, Joey Tianyi Zhou, Junsong Yuan

ICCV 2019 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 198 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 anchor proposal branch (ablation)A2J · NYU Handmean 3D error (mm): 10.08 -> 8.61Improved
add anchor proposal branch (ablation)A2J · ITOP front-viewmAP: 80.1 -> 88.0Improved
add informative anchor point surrounding loss (ablation)A2J · NYU Handmean 3D error (mm): 9.00 -> 8.61Improved
add informative anchor point surrounding loss (ablation)A2J · ITOP front-viewmAP: 86.4 -> 88.0Improved
use separate branches for in-plane offset and depth instead of one branch (ablation)A2J · NYU Handmean 3D error (mm): 8.95 -> 8.61Improved
use separate branches for in-plane offset and depth instead of one branch (ablation)A2J · ITOP front-viewmAP: 87.4 -> 88.0Improved
anchor-based paradigm instead of global regression (ablation)ResNet-50 pose network · K2HPDPDJ (0.05): 61.5 -> 76.3Improved
anchor-based paradigm instead of FCN model (ablation)ResNet-50 pose network · K2HPDPDJ (0.05): 70.4 -> 76.3Improved
ImageNet pre-training (ablation)A2J · NYU Handmean 3D error (mm): 10.08 -> 8.61Improved
ImageNet pre-training (ablation)A2J · ITOP front-viewmAP: 87.3 -> 88.0Improved
deeper backbone ResNet-18 to ResNet-50 (ablation)A2J · NYU Handmean 3D error (mm): 9.32 -> 8.61Improved
deeper backbone ResNet-18 to ResNet-50 (ablation)A2J · NYU HandFPS: 192.25 -> 105.06Hurt

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