AI Paper Atlas

Research map / 3D vision / Human pose estimation

Real-time Holistic Robot Pose Estimation with Unknown States

Shikun Ban, Juling Fan, Xiaoxuan Ma, Wentao Zhu, Yu QIAO, Yizhou Wang

ECCV 2024 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 8 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
use a separate backbone for DepthNet (ablation)holistic robot pose network · Panda DRADD AUC: 79.98 -> 82.68Improved
pre-train DepthNet before joint training (ablation)holistic robot pose network · Panda DRADD AUC: 74.29 -> 82.68Improved
add KeypointNet as auxiliary task sharing the backbone (ablation)JointNet · Panda DRMean joint error (degrees): 14.49 -> 9.29Improved
replace direct translation regression with DepthNet and add KeypointNet (ablation)holistic robot pose network · Panda syntheticADDImproved
add mask and keypoint consistency self-supervision on real images (ablation)holistic robot pose network · Panda real datasetsADD AUCImproved
feed-forward regression instead of iterative render-and-comparerobot pose estimation · Panda 3CAM-AKinference time (ms): 570.8 -> 44.3Improved
holistic regression vs RoboPose on Panda 3CAM-XKrobot pose estimation · Panda 3CAM-XK (real)ADD AUC: 77.6 -> 76.0Hurt

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