AI Paper Atlas

Research map / 3D vision / Face and shape

GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes

Pradyumn Goyal, Dmitry Petrov, Sheldon Andrews, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Evangelos Kalogerakis

ICCV 2025 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 10 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 geometric self-supervised pretraining on unannotated segmented shapes (ablation)GEOPARD-u · PartNet-Mobility (unlabeled)Axis Error AE (deg): 10.67 -> 9.18Improved
add geometric pretraining (ablation)GEOPARD-u · PartNet-Mobility (unlabeled)Revolute accuracy R-ACC: 0.87 -> 0.92Improved
add geometric pretraining (ablation)GEOPARD-u · PartNet-Mobility (unlabeled)Point Error PE: 0.06 -> 0.05Improved
aggregate part features with a learnable articulation query instead of mean pooling (ablation)GEOPARD no pretraining · PartNet-Mobility (unlabeled)Point Error PE: 0.11 -> 0.09Improved
regress per-point displacement votes for the pivot instead of predicting it from the articulation token (ablation)GEOPARD no pretraining · PartNet-Mobility (unlabeled)Point Error PE: 0.09 -> 0.06Improved
displacement voting for pivot (ablation)GEOPARD no pretraining · PartNet-Mobility (unlabeled)Axis Error AE (deg): 10.56 -> 10.67No clear effect
use GEOPARD instead of CAGE in labeled conditionGEOPARD · PartNet-Mobility (labeled)Axis Error AE (deg): 11.41 -> 8.87Improved
use GEOPARD in labeled condition for motion typeGEOPARD · PartNet-Mobility (labeled)Revolute accuracy R-ACC: 0.98 -> 0.98No clear effect
remove semantic part labels (unlabeled condition)GEOPARD · PartNet-MobilityRevolute accuracy R-ACC: 0.98 -> 0.92Hurt
order pretraining axes by PCA eigenvalue instead of motion range (ablation)GEOPARD pretraining · PartNet-Mobilitytraining qualityImproved

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