AI Paper Atlas

Research map / 3D vision / Human pose estimation

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

Fangyun Wei, Xiao Sun, Hongyang Li, Jingdong Wang, Stephen Lin

ECCV 2020 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 171 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 Corner Point with Projection matching instead of Nearest Point (ablation)PointSetNet · COCO minival instance segmentationmask AP: 21.9 -> 27.0Improved
use Corner Point with Projection matching instead of Nearest Line (ablation)PointSetNet · COCO minival instance segmentationmask AP: 23.2 -> 27.0Improved
increase anchor points from 24 to 72 (ablation)PointSetNet · COCO minival instance segmentationmask AP: 26.7 -> 28.0Improved
regress from point-set anchors instead of center point (ablation)PointSetNet · COCO minival instance segmentationmask AP: 26.0 -> 27.0Improved
use mean pose anchor instead of center point anchor (ablation)PointSetNet · COCO val2017 keypointsAP: 16.9 -> 40.9Improved
use mean pose anchor instead of rectangle anchor (ablation)PointSetNet · COCO val2017 keypointsAP: 12.0 -> 40.9Improved
use 5 K-means canonical poses instead of mean pose (ablation)PointSetNet · COCO val2017 keypointsAP: 40.9 -> 43.8Improved
go from 5 to 7 K-means pose anchors (ablation)PointSetNet · COCO val2017 keypointsAP: 43.8 -> 43.8No clear effect
widen scale range of pose anchors from 0.6:1.4 to 0.4:1.6 (ablation)PointSetNet · COCO val2017 keypointsAP: 42.6 -> 39.4Hurt
widen rotation range of pose anchors from -20:20 to -30:30 (ablation)PointSetNet · COCO val2017 keypointsAP: 43.5 -> 42.6Hurt
use deep shape indexed feature instead of box region feature (9 points) (ablation)PointSetNet · COCO val2017 keypointsAP: 42.8 -> 46.0Improved
apply shape indexed feature only to classification subnetwork (ablation)PointSetNet · COCO val2017 keypointsAP: 41.6 -> 46.0Mixed

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