AI Paper Atlas

Research map / 3D vision / Human pose estimation

Orientation Keypoints for 6D Human Pose Estimation

Martin Fisch, Ronald Clark

TPAMI 2021 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 27 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 3D detections with SVD instead of 2D detections with PnP (ablation)orientation keypoints · Human3.6M rotationsMPJPAS rad: 0.265 -> 0.213Improved
add orientation keypoints to joint keypoints (lifter, ground-truth 2D) (ablation)lifter · Human3.6MMPJPE mm: 48.3 -> 33.3Improved
add orientation keypoints to Crosshairs 2D detections (ablation)lifter · Human3.6MMPJPE mm: 50.6 -> 47.1Improved
add orientation keypoints to regression 2D detections (ablation)lifter · Human3.6MMPJPE mm: 57.8 -> 53.0Improved
use Crosshairs 3D detector instead of Crosshairs 2D (ablation)lifter with OKPs · Human3.6MMPJPE mm: 47.1 -> 44.6Improved
use Crosshairs instead of regression 2D detector (ablation)lifter with OKPs · Human3.6MMPJPE mm: 53.0 -> 47.1Improved
raise resolution from 256x192 to 384x288 (ablation)Crosshairs 1-layer XY · Human3.6MMPJPE-17 P1 mm: 52.2 -> 48.1Improved
use 4-layer instead of 1-layer XY crosshairs (ablation)Crosshairs 384x288 · Human3.6MMPJPE-17 P1 mm: 48.1 -> 48.2No clear effect
add second-stage refiner (ablation)Crosshairs 384x288 1-layer · Human3.6MMPJPE-17 P1 mm: 48.1 -> 45.5Improved
train with feet/hands included (21j, 19r) (ablation)Crosshairs 384x288 4-layer · Human3.6MMPJPE-17 P1 mm: 48.2 -> 47.4Improved
add centroid regularizer loss (ablation)Crosshairs · Human3.6MaccuracyNo clear effect
fine-tune on 3DPW and use orientation keypointsorientation kps · 3DPWMPJPE mm: 115.4 -> 70.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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