AI Paper Atlas

Research map / 3D vision / Face and shape

Tracking-by-Detection of 3D Human Shapes: From Surfaces to Volumes

Chun-Hao P. Huang, Benjamin Allain, Edmond Boyer, Jean-Sébastien Franco, Federico Tombari, Nassir Navab, Slobodan Ilić

TPAMI 2017 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 17 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 random-forest discriminative associations instead of ICP (surICP) at low frame ratesurface tracking · Jumping (every third frame)silhouette overlap error: 16759.29 -> 9148.94Improved
use discriminative associations instead of surICP at low frame ratesurface tracking · Crane (every third frame)silhouette overlap error: 8295.58 -> 7746.40Improved
use discriminative associations instead of surICP at low frame ratesurface tracking · Bouncing (every third frame)silhouette overlap error: 9400.76 -> 6847.72Improved
use discriminative associations instead of surICP at low frame ratesurface tracking · Handstand (every third frame)silhouette overlap error: 11690.61 -> 9279.57Improved
use discriminative associations instead of surICP at full frame ratesurface tracking · sequences without outlierssilhouette overlap errorNo clear effect
use CVT-based fully volumetric tracking instead of voxel-based pipeline [11]tracking-by-detection · Thomas/Seq2silhouette pixel error mean: 28731 -> 9991Improved
use CVT-based tracking instead of voxel-based [11]tracking-by-detection · Ballet/Seq2silhouette pixel error mean: 5427 -> 2620Improved
use CVT-based tracking instead of voxel-based [11]tracking-by-detection · Goalkeeper/UpJumpsilhouette pixel error mean: 19838 -> 15221Improved
use CVT-based tracking instead of voxel-based [11]tracking-by-detection · Ballet/Seq2 markersmean marker error (mm): 124.02 -> 26.37Improved
use proposed instead of ICP-based Allain et al. [51]tracking-by-detection · Goalkeeper/UpJumpsilhouette pixel error mean: 14773 -> 15221No clear effect
use proposed instead of Allain et al. [51]tracking-by-detection · Ballet/Seq2 markersmean marker error (mm): 27.82 -> 26.37Improved
train forest across all three subjects (cross-template) instead of Goalkeeper only (ablation)CVT forest · Goalkeeper/UpJump correspondencescorrespondence accuracyNo clear effect

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