AI Paper Atlas

Research map / 3D vision / Human pose estimation

Self6D: Self-Supervised Monocular 6D Object Pose Estimation

Gu Wang, Fabian Manhardt, Jianzhun Shao, Xiangyang Ji, Nassir Navab, Federico Tombari

ECCV 2020 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose

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 mask alignment loss L_mask (ablation)Self6D · LineMODAverage Recall ADD(-S) (%): 0.1 -> 58.9Improved
add geometric alignment loss L_geom (ablation)Self6D · LineMODAverage Recall ADD(-S) (%): 6.4 -> 58.9Improved
add MS-SSIM loss (ablation)Self6D · LineMODAverage Recall ADD(-S) (%): 56.3 -> 58.9Improved
add perceptual loss (ablation)Self6D · LineMODAverage Recall ADD(-S) (%): 58.1 -> 58.9Improved
add LAB color loss L_ab (ablation)Self6D · LineMODAverage Recall ADD(-S) (%): 58.5 -> 58.9Improved
apply self-supervision on unannotated real RGB-D dataSelf6D-LB · LineMODAverage Recall ADD(-S) (%): 40.1 -> 58.9Improved
apply self-supervision on unannotated real RGB-D dataSelf6D-LB · LineMOD OcclusionAverage Recall ADD(-S) (%): 15.1 -> 32.1Improved
apply self-supervision on real training setSelf6D-LB · Cropped LineMODmean angle error (deg): 19.8 -> 15.8Improved
apply self-supervision on 10% real RGB-D imagesSelf6D-LB · YCB-Video (5 objects)Average Recall ADD(-S) (%): 29.9 -> 48.6Improved
increase amount of unlabeled real data to about 40%Self6D · HomebrewedDBmean average recall (%): 31% -> 71%Improved

Later papers that compared with this method

6 later accepted papers report Self6D++ as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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