AI Paper Atlas

Research map / 3D vision / Human pose estimation

Category-Level 6D Object Pose and Size Estimation Using Self-Supervised Deep Prior Deformation Networks

Jiehong Lin, Zewei Wei, Changxing Ding, Kui Jia

ECCV 2022 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 94 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 Deep Prior Deformer (ablation)DPDN with parallel learning · REAL275 test (supervised)mAP 5deg 2cm: 35.2 -> 46.0Improved
add Deep Prior Deformer (ablation)DPDN single input · REAL275 test (supervised)mAP 5deg 2cm: 26.7 -> 39.6Improved
add Pose and Size Estimator instead of Umeyama on canonical points (ablation)DPDN · REAL275 test (supervised)mAP IoU50: 59.6 -> 83.4Improved
add parallel dual-input supervision (ablation)DPDN with deformer · REAL275 test (supervised)mAP 5deg 2cm: 39.6 -> 46.0Improved
add parallel dual-input supervision (ablation)DPDN without deformer · REAL275 test (supervised)mAP 5deg 2cm: 26.7 -> 35.2Improved
add parallel dual-input supervision (ablation)DPDN with deformer · REAL275 test (supervised)mAP IoU75: 76.2 -> 76.0No clear effect
add inter-consistency loss (ablation)DPDN · REAL275 test (unsupervised)mAP 5deg 2cm: 29.7 -> 36.9Improved
add intra-consistency losses (ablation)DPDN · REAL275 test (unsupervised)mAP 5deg 2cm: 29.7 -> 35.8Improved
add intra-consistency losses without inter-consistency (ablation)DPDN · REAL275 test (unsupervised)mAP IoU75: 60.8 -> 58.6Hurt
combine inter- and intra-consistency (ablation)DPDN · REAL275 test (unsupervised)mAP 5deg 2cm: 29.7 -> 37.8Improved
add unlabeled real-world images via self-supervision (ablation)DPDN · REAL275 test (unsupervised)mAP 5deg 2cm: 29.7 -> 37.8Improved
increase ratio of unlabeled real training data (ablation)Self-DPDN · REAL275 test (unsupervised)mAPImproved

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