AI Paper Atlas

Research map / 3D vision / Human pose estimation

Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation

Kiru Park, Timothy Patten, Markus Vincze

ICCV 2019 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 546 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 transformer loss instead of plain L1 loss for symmetric objects (ablation)Pix2Pose · T-Less obj-05VSD recall: 33.4 -> 55.2Improved
add transformer loss instead of L1 loss with view limits (ablation)Pix2Pose · T-Less obj-05VSD recall: 47.2 -> 55.2Improved
add the second-stage refinement with re-centered bounding box (ablation)Pix2Pose · LineMODADD-10% recall: 41 -> 72.4Improved
add GAN loss to training (ablation)Pix2Pose · LineMOD (artificially occluded test images)fraction of correct posesImproved
add GAN loss to training (ablation)Pix2Pose · LineMOD (fully visible objects)fraction of correct posesNo clear effect
use a convex hull instead of the precise 3D model for training (ablation)Pix2Pose · LineMODADD fractionHurt
use Retinanet instead of SSD-6D as 2D detector (ablation)Pix2Pose · LineMODADD-10% correct poses: 64.0 -> 71.1Improved
use Faster R-CNN instead of Retinanet as 2D detector (ablation)Pix2Pose · LineMODADD-10% correct poses: 71.1 -> 72.4Improved
use ground-truth boxes instead of Faster R-CNN detections (ablation)Pix2Pose · LineMODADD-10% correct poses: 72.4 -> 74.7Improved
detector choice, restricted to scenes with correct boxes (ablation)Pix2Pose · LineMODADD-10% correct poses: 70.9 -> 73.2No clear effect

Later papers that compared with this method

8 later accepted papers report Pix2Pose as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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