AI Paper Atlas

Research map / 3D vision / Human pose estimation

RAVEN: End-to-end Equivariant Robot Learning with RGB Cameras

David Klee, Boce Hu, Andrew Cole, Heng Tian, Dian Wang, Robert Platt, Robin Walters

ICLR 2026 · 3D vision › Human pose estimation · approach: Category-level pose estimation

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 SE(3) ray encoding (patch orientation) (ablation)RAVEN · MimicGen ablation subset (4 tasks)success rate (%): 72 -> 76Improved
add equivariant decoder (ablation)RAVEN · MimicGen ablation subset (4 tasks)success rate (%): 72 -> 76Improved
add equivariant encoder and decoder (ablation)RAVEN · MimicGen ablation subset (4 tasks)success rate (%): 58 -> 76Improved
use RAVEN instead of EquiDiffPopolicy · MimicGen (12 tasks, 100 demos)success rate (%): 54 -> 66Improved
use RAVEN architecture over DiffPo with same pretrained ResNetDiffPo (Pre) · MimicGen (12 tasks, 100 demos)success rate (%): 52 -> 66Improved
use pretrained ResNet encoder in DiffPoDiffPo · MimicGen (12 tasks, 100 demos)success rate (%): 42 -> 52Improved
use RAVEN on bimanual taskspolicy · DexMimicGen (6 tasks, 50 demos)success rate (%): 65 -> 82Improved
use RAVEN under perturbed camera viewspolicy · MimicGen perturbed agent-view camera (4 tasks)success rate (%): 48 -> 71Improved
use RAVEN on real-world taskspolicy · Real-world UR5 (4 tasks)success rate (%): 24 -> 63Improved
use RAVEN instead of EquiDiffPo for training speedpolicy · MimicGen Threading D2training time (hours): 7.3 -> 2.8Improved
add camera-parameter augmentation at test time under calibration noiseRAVEN · MimicGen subset (calibration noise)success rate (%): dropping only 1%Improved

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