AI Paper Atlas

Research map / 3D vision / Human pose estimation

Face-from-Depth for Head Pose Estimation on Depth Images

Guido Borghi, Matteo Fabbri, Roberto Vezzani, Simone Calderara, Rita Cucchiara

TPAMI 2018 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 105 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 head crop around ground-truth head position to depth-only network (ablation)depth CNN · Pandora head poseaccuracy: 0.553 -> 0.646Improved
add FfD branch to depth branch via concatenation (ablation)POSEidon+ · Pandora head poseaccuracy: 0.646 -> 0.698Improved
add Motion Images branch to depth branch via concatenation (ablation)POSEidon+ · Pandora head poseaccuracy: 0.646 -> 0.690Improved
add Motion Images as third branch to depth+FfD with conv+concat fusion (ablation)POSEidon+ · Pandora head poseaccuracy: 0.698 -> 0.736Improved
replace gray-level-trained branch with FfD-generated input branch (ablation)POSEidon+ · Pandora head poseaccuracy: 0.720 -> 0.736Improved
use new det-cGAN FfD instead of preliminary FfD in the frameworkPOSEidon+ · Pandora head poseaccuracy: 0.715 -> 0.736Improved
add U-Net skip connections to the FfD generator (ablation)FfD · Pandora face reconstructionL1 norm: 18.21 -> 23.75Hurt
use det-cGAN FfD instead of pix2pix for reconstructionFfD · Pandora head pose (gray-trained net)accuracy: 0.581 -> 0.613Improved
test gray-trained pose net on FfD faces instead of real gray-levelhead pose network · Pandora head pose (gray-trained net)accuracy: 0.613 -> 0.613No clear effect
crop shoulder input with Rx=850, Ry=500 (ablation)shoulder pose network · Pandora shoulder poseaccuracy: 0.877 -> 0.924Improved
use narrow shoulder crop Rx=700, Ry=250 (ablation)shoulder pose network · Pandora shoulder poseaccuracy: 0.877 -> 0.845Hurt
POSEidon+ versus preliminary POSEidonPOSEidon+ · Biwi (fixed split)avg angle error: 1.7 -> 1.6Improved

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