AI Paper Atlas

Research map / 3D vision / Human pose estimation

KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects

Xingyu Liu, Rico Jonschkowski, Anelia Angelova, Kurt Konolige

CVPR 2020 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 133 citations (OpenAlex)

Check 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 stereo RGB instead of monocular input (ablation)KeyPose · TOD bottle_03D MAE (mm): 10.0 -> 4.6Improved
Use stereo RGB instead of monocular input (ablation)KeyPose · TOD bottles3D MAE (mm): 10.1 -> 5.8Improved
Fuse the stereo views early rather than late (ablation)KeyPose · TOD bottle_03D MAE (mm): 7.9 -> 4.6Improved
Fuse the stereo views early rather than late (ablation)KeyPose · TOD bottles3D MAE (mm): 10.6 -> 5.8Improved
Add projection loss (ablation)KeyPose · TOD bottle_03D MAE (mm): 5.4 -> 4.6Improved
Add projection loss (ablation)KeyPose · TOD bottles3D MAE (mm): 9.9 -> 5.8Improved
Use direct regression instead of integral projection (ablation)KeyPose · TOD bottle_03D MAE (mm): 4.7 -> 4.6Improved
Use direct regression instead of integral projection (ablation)KeyPose · TOD bottles3D MAE (mm): 6.0 -> 5.8Improved
Add permutation loss for symmetric keypoints (ablation)KeyPose · TOD tree_03D MAE (mm): 26.4 -> 12.8Improved
Increase crop size to 270x180 (ablation)KeyPose · TOD bottle_03D MAE (mm): 4.6 -> 5.0Hurt
Increase crop size to 360x240 (ablation)KeyPose · TOD bottle_03D MAE (mm): 4.6 -> 5.3Hurt
Use stereo RGB keypoint estimation rather than DenseFusion with opaque depthKeyPose vs DenseFusion · TOD instance-level, held-out textures (mean)MAE: 35.1 -> 9.9Improved

Later papers that compared with this method

1 later accepted paper reports KeyPose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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