AI Paper Atlas

Research map / 3D vision / Human pose estimation

Real-Time Monocular Pose Estimation of 3D Objects Using Temporally Consistent Local Color Histograms

Henning Tjaden, Ulrich Schwanecke, Elmar Schomer

ICCV 2017 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 123 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 averaged posteriors (8) instead of averaged local energies (5) (ablation)tclc-histogram detection · ACCV dataset, 100 training images2D IoU score: 68.5% -> 78.5%Improved
use averaged posteriors (8) instead of averaged local energies (5) (ablation)tclc-histogram detection · ACCV dataset, 100 training images2D projection score: 28.8% -> 40.2%Improved
use averaged posteriors (8) instead of averaged local energies (5) (ablation)tclc-histogram detection · ACCV dataset, 100 training images6D pose score [11]: 49.8% -> 57.3%Improved
use averaged posteriors (8) instead of averaged local energies (5) (ablation)tclc-histogram detection · ACCV dataset, 100 training images6D pose score [25]: 18.6% -> 26.7%Improved
use averaged posteriors (8) instead of averaged local energies (5) (ablation)tclc-histogram tracking · Semi-synthetic driller sequencesilhouette pose ambiguity count: twice -> onceImproved
add temporal consistency to local color histograms (ablation)local histogram segmentation · Semi-synthetic driller sequencetracking successImproved
replace global histograms by local tclc-histogramstracking of [26] · Semi-synthetic driller sequencetracking successImproved
replace global histograms by local tclc-histogramstracking of [26] · Real drill sequence with cluttertracking successImproved
add temporal consistency to local color histograms (ablation)local histogram segmentation · Real drill sequence with cluttertracking successImproved
use averaged posteriors (8) instead of (5) for pose recovery (ablation)tclc-histogram pose detection · Real drill sequence with clutterrecovery after leaving field of viewImproved
increase number of training images from 25 to 200tclc-histogram detection · ACCV datasetdetection scoreImproved
compare against LINE-2D on 2D IoUtclc-histogram detection · ACCV dataset, 100 training images2D IoU score: 86.5% -> 78.5%Hurt

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