AI Paper Atlas

Research map / 3D vision / Human pose estimation

Neural Object Learning for 6D Pose Estimation Using a Few Cluttered Images

Kiru Park, Timothy Patten, Markus Vincze

ECCV 2020 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 18 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 pose refinement of source images (ablation)NOL · SMOT rendered image qualityperceptual similarity (lower is better): 0.181 -> 0.173Improved
add decoder block (ablation)NOL · SMOT rendered image qualityperceptual similarity (lower is better): 0.289 -> 0.173Improved
add LSTM module instead of simple average (ablation)NOL · SMOT rendered image qualityperceptual similarity (lower is better): 0.241 -> 0.173Improved
add perceptual loss to L1 loss (ablation)NOL · SMOT rendered image qualityperceptual similarity (lower is better): 0.184 -> 0.177Improved
add smooth loss to L1 and perceptual loss (ablation)NOL · SMOT rendered image qualityperceptual similarity (lower is better): 0.177 -> 0.173Improved
add adversarial GAN loss (ablation)NOL · SMOT rendered image qualityperceptual similarity (lower is better): 0.173 -> 0.183Hurt
train Pix2Pose on NOL images instead of synthetic images from 3D modelsPix2Pose · LineMOD RGBADD average: 16.6 -> 49.5Improved
train on NOL images instead of synthetic images, with ICPPix2Pose + ICP · LineMOD RGB+ICPADD average: 78.8 -> 96.3Improved
train on NOL images instead of synthetic imagesPix2Pose · LineMOD-Occ RGBBOP score: 20.0 -> 37.7Improved
add ICP3D refinement with NOL trainingPix2Pose · LineMOD-OccBOP score: 37.7 -> 61.3Improved
train on NOL images instead of real images (precise models)Pix2Pose · SMOT RGBAD{D|I} score: 25.0 -> 35.5Improved
render NOL images with NOL instead of G2Ltex texturesPix2Pose · SMOT RGBAD{D|I} score: 25.7 -> 35.5Improved

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