AI Paper Atlas

Research map / 3D vision / Human pose estimation

EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks

Athinoulla Konstantinou, Georgios Leontidis, Mamatha Thota, Aiden Durrant

ICCV 2025 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 0 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
replace predictor-based equivariance with predictor-free capsule pose matricesEquiCaps · 3DIEBench-T rotation (rotation-only pretraining)Rotation R2: 0.45 -> 0.73 vs SIEImproved
use EquiCaps instead of invariant-only or predictor-based methods for classificationEquiCaps · 3DIEBench classificationTop-1 accuracy: 83.24 vs 87.44 for SimCLR + AugSelfHurt
add invariance loss to the equivariance objective (ablation)EquiCaps · 3DIEBench classificationTop-1 accuracy: 81.43 -> 83.24Improved
apply variance-covariance regularisation on concatenated activations and poses instead of pose only (ablation)EquiCaps · 3DIEBench classificationTop-1 accuracy: 81.68 -> 82.40Improved
increase number of capsules from 16 to 64 (ablation)EquiCaps · 3DIEBench classificationTop-1 accuracy: 81.89 -> 83.66Improved
increase capsules from 32 to 64 under rotation-only pretraining (ablation)EquiCaps · 3DIEBench-T translationTranslation R2: 0.60 -> 0.53Hurt
add translation to pretraining objectiveSIE · 3DIEBench-T translationTranslation R2: 0.20 -> 0.22No clear effect
use capsule projector rather than MLP predictors on ViT-Tiny/16 backboneEquiCaps · 3DIEBench rotation (ViT-Tiny/16)Rotation R2: 0.39 -> 0.71 vs SIEImproved
evaluate on embeddings instead of representationsinvariant SSL methods · 3DIEBench rotationRotation R2: 0.45-0.52 -> 0.24Hurt
use EquiCaps for faster convergenceEquiCaps · 3DIEBench rotationRotation R2: 0.75 at 100 epochs vs SIE 0.29, CapsIE 0.31Improved

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