AI Paper Atlas

Research map / 3D vision / Human pose estimation

DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation

Ivan Shugurov, Sergey Zakharov, Slobodan Ilić

TPAMI 2021 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 60 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 4 calibrated-view refinementDPODv2 RGB · Linemod (real train)ADD recall: 93.59 -> 99.91Improved
add 4 calibrated-view refinementDPODv2 RGB · Linemod (synthetic train)ADD recall: 81.20 -> 99.70Improved
add 4 calibrated-view refinementDPODv2 RGB · Homebrewedaverage recall: 0.725 -> 0.835Improved
add ICP refinementDPODv2 + Kabsch · TLESS (PBR train)average recall: 0.699 -> 0.590Hurt
add ICP refinementDPODv2 + Kabsch · Occlusion (PBR train)average recall: 0.700 -> 0.698No clear effect
use depth CENet instead of RGB CENetDPODv2 · Homebrewedaverage recall: 0.725 -> 0.382Hurt
use RGB correspondences with depth Kabsch instead of RGB-only PnPDPODv2 · Homebrewedaverage recall: 0.725 -> 0.84Improved
train correspondence network on depth instead of RGBDPODv2 · Linemod (synthetic train)ADD recall: 99.22 -> 88.94Hurt
choose furthest instead of closest views for refinement (2 views) (ablation)multi-view refiner · Linemod (real train)ADD recall: 86.43 -> 99.71Improved
choose random instead of closest views for refinement (2 views) (ablation)multi-view refiner · Homebrewed (synthetic)average recall: 0.693 -> 0.808Improved
choose furthest instead of closest views (4 views) (ablation)multi-view refiner · Linemod (real train)ADD recall: 96.53 -> 99.97Improved
train correspondence network on synthetic instead of real data (GT patches)DPODv2 · TLESSaverage recall: 0.535 -> 0.729Improved

Later papers that compared with this method

1 later accepted paper reports DpodV2 as a baseline in their results tables; 0 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 5 of 5 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