AI Paper Atlas

Research map / 3D vision / Human pose estimation

Reconstruct Locally, Localize Globally: A Model Free Method for Object Pose Estimation

Ming Cai, Ian Reid

CVPR 2020 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 36 citations (OpenAlex)

Check 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 multi-view landmark alignment loss to reprojection loss (ablation)RLLG object-coordinate head · Expo test set5cm5deg: 14.3 -> 39.3Improved
Add multi-view landmark alignment loss to reprojection loss (ablation)RLLG object-coordinate head · Expo test setADD-10: 23.6 -> 52.5Improved
Add photometric loss to reprojection loss (ablation)RLLG object-coordinate head · Expo test set5cm5deg: 14.3 -> 40.1Improved
Add photometric loss to reprojection loss (ablation)RLLG object-coordinate head · Expo test setADD-10: 23.6 -> 51.3Improved
Add landmark alignment and photometric losses to reprojection loss (ablation)RLLG object-coordinate head · Expo test set5cm5deg: 14.3 -> 53.1Improved
Add landmark alignment and photometric losses to reprojection loss (ablation)RLLG object-coordinate head · Expo test setADD-10: 23.6 -> 58.5Improved
Use reprojection loss alone instead of direct depth supervision (ablation)RLLG object-coordinate head · Expo test set5cm5deg: 61.3 -> 14.3Hurt
Use reprojection loss alone instead of direct depth supervision (ablation)RLLG object-coordinate head · Expo test setADD-10: 57.1 -> 23.6Hurt
Use the model-free RLLG method instead of Dense-FusionLINEMOD · LINEMODADD-10: 94 -> 82.88Hurt
Use the model-free RLLG method instead of PVNetOcclusion LINEMOD · Occlusion LINEMODADD-10: 40.8 -> 30.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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