AI Paper Atlas

Research map / 3D vision / Human pose estimation

GTCaR: Graph Transformer for Camera Re-Localization

Xinyi Li, Haibin Ling

ECCV 2022 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 8 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 graph Transformer layers (vs temporal only) (ablation)GTCaR · Cambridge Courtmedian translation error (m): 6.95 -> 5.62Improved
add graph Transformer layers (vs temporal only) (ablation)GTCaR · Oxford RobotCar LOOPmedian translation error (m): 8.25 -> 5.46Improved
add graph Transformer layers (vs temporal only) (ablation)GTCaR · 7-Scenes Pumpkinmedian translation error (m): 0.31 -> 0.15Improved
add temporal Transformer layers (vs graph only) (ablation)GTCaR · Cambridge Courtmedian translation error (m): 7.34 -> 5.62Improved
add temporal Transformer layers (vs graph only) (ablation)GTCaR · Oxford RobotCar LOOPmedian translation error (m): 9.03 -> 5.46Improved
add temporal Transformer layers (vs graph only) (ablation)GTCaR · 7-Scenes Pumpkinmedian translation error (m): 0.17 -> 0.15No clear effect
add MPNN layers with adjacency tensor (ablation)GTCaR · Oxford RobotCar LOOPmedian translation error (m): 7.95 -> 5.46Improved
add MPNN layers with adjacency tensor (ablation)GTCaR · Cambridge Courtmedian translation error (m): 5.98 -> 5.62Improved
add MPNN layers with adjacency tensor (ablation)GTCaR · 7-Scenes Pumpkinmedian translation error (m): 0.20 -> 0.15Improved
use GTCaR graph Transformer instead of CNN+GNNCNN+GNN · Oxford RobotCar LOOPmedian translation error (m): 8.15 -> 5.46Improved
use GTCaR instead of CNN+GNNCNN+GNN · Oxford RobotCar FULLmedian rotation error (deg): 3.47 -> 3.68Hurt
use GTCaR instead of CNN+GNNCNN+GNN · Cambridge (average of first four scenes)median translation error (m): 1.12 -> 0.98Improved

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