AI Paper Atlas

Research map / 3D vision / Human pose estimation

Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation

Ruiqi Wang, Xinggang Wang, Te Li, Rong Yang, Minhong Wan, Wenyu Liu

ICCV 2023 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 36 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
replace sparse learnable queries with pre-learned point-cloud prior plus PointNet++ (ablation)Query6DoF · REAL2755°2cm: 49.0 -> 47.2Hurt
add global enhancement block (ablation)Query6DoF · REAL2755°2cm: 44.2 -> 49.0Improved
add queries deformation estimator (ablation)Query6DoF · REAL2755°2cm: 46.5 -> 49.0Improved
add query deformation and query-point correspondence estimators (ablation)Query6DoF · REAL2755°2cm: 35.4 -> 49.0Improved
regress pose directly with a pose and size estimator instead of Umeyama on Pr and Pi (ablation)Query6DoF · REAL2755°2cm: 40.0 -> 49.0Improved
increase number of queries from 64 to 1024 (ablation)Query6DoF · REAL2755°2cm: 49.0 -> 48.7No clear effect
reduce number of queries from 64 to 16 (ablation)Query6DoF · REAL2755°2cm: 49.0 -> 46.0Mixed
use sigmoid with learnable alpha instead of softmax for attention normalization (ablation)Query6DoF · REAL275IoU75: 74.7 -> 76.1Improved
use sparse learnable queries as shape prior instead of SPD point-cloud priorcategory-level pose estimation · REAL2755°2cm: 19.3 -> 49.0Improved
add linear and non-linear shape augmentation (ablation)Query6DoF · REAL2755°2cm: 46.8 -> 49.0Improved

Later papers that compared with this method

2 later accepted papers report Query6DoF as a baseline in their results tables; 2 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