AI Paper Atlas

Research map / 3D vision / Human pose estimation

Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation

Gu Wang, Fabian Manhardt, Xingyu Liu, Xiangyang Ji, Federico Tombari

TPAMI 2021 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 72 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 self-supervision with unlabeled real RGB-D dataOURS(LB) · Occluded LINEMOD (BOP test)average recall ADD(-S): 52.9% -> 64.7%Improved
add self-supervision with unlabeled real RGB data onlyOURS(LB) · Occluded LINEMOD (BOP test)average recall ADD(-S): 52.9 -> 59.8Improved
add self-supervision on a few unlabeled HomebrewedDB images (RGB-D)OURS(LB) · HomebrewedDBaverage recall ADD(-S): 3.1% -> 84.4%Improved
add self-supervision (RGB-D)OURS(LB) · LINEMODaverage recall ADD(-S): 77.4 -> 88.5Improved
add self-supervision (RGB-D)OURS(LB) · YCB-VideoAUC of ADD(-S): 77.8 -> 80.0Improved
add self-supervision (RGB-D)OURS(LB) · Cropped LINEMODmean angle error (deg): 11.2 -> 3.9Improved
add geometric loss Lgeom (ablation)Self6D++ RGB-D · Occluded LINEMOD (BOP test)average recall ADD(-S): 5.1% -> 64.7%Improved
add amodal mask prediction (ablation)Self6D++ RGB-D · Occluded LINEMOD (BOP test)average recall ADD(-S): 55.1% -> 64.7%Improved
add data augmentation on student input (noisy student) (ablation)Self6D++ RGB-D · Occluded LINEMOD (BOP test)average recall ADD(-S): 62.1% -> 64.7%Improved
add visual loss Lvisual (ablation)Self6D++ RGB-D · Occluded LINEMOD (BOP test)average recall ADD(-S): 63.2 -> 64.7Improved
add point matching loss Lpm (ablation)Self6D++ RGB-D · Occluded LINEMOD (BOP test)average recall ADD(-S): 64.3 -> 64.7Improved
predict both amodal and visible masks instead of visible only (ablation)Self6D++ · LINEMODaverage recall ADD(-S): 88.3 -> 88.5No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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