AI Paper Atlas

Research map / 3D vision / Human pose estimation

FoundPose: Unseen Object Pose Estimation with Foundation Features

Evin Pınar Örnek, Yann Labbé, Bugra Tekin, Lingni Ma, Cem Keskin, Christian Forster, Tomas Hodan

ECCV 2024 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 88 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
use layer 18 instead of the last layer 23 of DINOv2 ViT-L for patch descriptors (ablation)FoundPose · BOP 7 datasets averageAverage AR: 23.5 -> 37.2Improved
use DINOv2 patch descriptors instead of SAM, DenseSIFT or S2DNet (ablation)FoundPose · BOP 7 datasets averageAverage AR: 37.2 vs 10.7 (SAM), 7.6 (DenseSIFT), 1.1 (S2DNet)Improved
use bag-of-words template retrieval from patch descriptors instead of cls token matching (ablation)FoundPose · BOP 7 datasets averageAverage AR: 18.2 -> 37.2Improved
mask background black for cls token retrieval (ablation)cls token retrieval · BOP 7 datasets averageAverage AR: 18.2 -> 25.1Improved
add featuremetric refinement to coarse poseFoundPose · BOP 7 datasets averageAverage AR: 37.2 -> 42.6Improved
add MegaPose refiner to FoundPose coarse posesFoundPose · BOP 7 datasets averageAverage AR: 37.2 -> 54.7Improved
refine 5 hypotheses with featuremetric plus MegaPose instead of 1FoundPose · BOP 7 datasets averageAverage AR: 55.0 -> 59.6Improved
add featuremetric refinement before MegaPose refinementFoundPose · BOP 7 datasets averageAverage AR: 54.7 -> 55.0Improved
use ground-truth masks instead of CNOS masks (ablation)FoundPose · BOP datasets with public GTAR: +6--19 ARImproved
vary number of templates, PCA components, visual words, RANSAC iterations (ablation)FoundPose · BOPAverage ARNo clear effect
replace ViT-L backbone with ViT-S (layer 9) (ablation)FoundPose · BOP 7 datasets averageAverage AR: 37.2 -> 34.0Hurt

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