AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Articulated Shape With Keypoint Pseudo-Labels From Web Images

Anastasis Stathopoulos, Georgios Pavlakos, Ligong Han, Dimitris N. Metaxas

CVPR 2023 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 7 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 consistency-selected web keypoint pseudo-labels to ACSM-oursACSM-ours · Pascal Horse, Cow, and SheepAUC: 50.8 -> 55.9; 47.6 -> 52.6; 46.8 -> 53.0Improved
Add consistency-selected web keypoint pseudo-labels to ACSM-oursACSM-ours · Animal Pose Horse, Cow, and SheepAUC: 66.7 -> 75.1; 59.6 -> 69.6; 57.2 -> 60.2Improved
Add consistency-selected web keypoint pseudo-labels to ACSM-oursACSM-ours · COCO Giraffe and BearAUC: 79.1 -> 86.6; 59.2 -> 63.4Improved
Use all web pseudo-labels rather than curating a subset (ablation)ACSM-ours · Pascal Horse, Cow, and SheepAUC: 50.8 -> 50.2; 47.6 -> 43.9; 46.8 -> 43.5Hurt
Use all web pseudo-labels rather than curating a subset (ablation)ACSM-ours · Animal Pose SheepAUC: 57.2 -> 29.1Hurt
Use all web pseudo-labels rather than curating a subset (ablation)ACSM-ours · COCO Giraffe and BearAUC: 79.1 -> 75.6; 59.2 -> 58.2Hurt
Select pseudo-labels by consistency rather than keypoint confidence alone (ablation)ACSM-ours with web pseudo-labels · Pascal, Animal Pose, and COCOAUCImproved
Use keypoint pseudo-labels from unlabeled imagesCMR · CUB3D reconstruction performanceImproved
Reduce the labeled set while retaining 3K selected pseudo-labeled images (ablation)ACSM horse reconstruction · Pascal HorseAUCImproved
Use CF-CM² consistency filtering (ablation)ACSM-ours with selected web pseudo-labels · Pascal Horse camera viewpointerr_R: 30.2 -> 28.1Improved
Use CF-CM² consistency filtering (ablation)ACSM-ours with selected web pseudo-labels · Pascal Cow camera viewpointerr_R: 34.7 -> 32.7Improved

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