AI Paper Atlas

Research map / 3D vision / Human pose estimation

Pose Correction for Highly Accurate Visual Localization in Large-Scale Indoor Spaces

Janghun Hyeon, Joohyung Kim, Nakju Doh

ICCV 2021 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 28 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 pose correction (re-estimate pose with reorganized local features) (ablation)coarse-to-fine localization baseline · InLoc DUC2accuracy within 1.0 m: 87.0 -> 93.9Improved
add pose correction (ablation)coarse-to-fine localization baseline · InLoc DUC1accuracy within 1.0 m: 85.9 -> 89.4Improved
add pose correction (ablation)coarse-to-fine localization baseline · M-siteaccuracy within 0.5 m: 65.9 -> 68.9Improved
add pose update step to candidates (ablation)baseline with 10 candidates · InLoc DUC2accuracy within 0.5 m: 82.4 -> 90.1Improved
add reranking by inlier count (K2 = 20) (ablation)pose correction · InLoc DUC2accuracy within 0.25 m: 67.2 -> 67.9Improved
use modified pose verification (MPV) instead of PV (ablation)proposed pipeline · InLoc DUC2accuracy within 1.0 m: 90.8 -> 93.9Improved
use modified pose verification (MPV) instead of PV (ablation)baseline pipeline · InLoc DUC1 and DUC2accuracy within 1.0 m: DUC1 85.9 -> 88.4, DUC2 87.0 -> 85.5Mixed
add divided matching instead of full matching (ablation)pose correction without inter-pose · InLoc DUC1 and DUC2accuracy within 0.5 m / 0.25 m: DUC2 0.25 m 67.9 -> 69.5, DUC1 0.5 m 76.8 -> 75.8Mixed
add inter-pose matching (ablation)pose correction with divided matching and normal filtering · InLoc DUC2accuracy within 0.25 m: 67.2 -> 71.0Improved
add VLF map (ablation)pose correction with full matching · InLoc DUC1accuracy within 1.0 m: 89.4 -> 90.4Improved
add point normal filtering (ablation)pose correction with VLF map and divided matching · InLoc DUC1 and DUC2accuracy within 1.0 m: DUC2 92.4 -> 93.9, DUC1 90.9 -> 89.9Mixed
increase SuperPoint features from 3,000 to 4,096pose correction · InLoc DUC1 and DUC2accuracy within 1.0 m: DUC1 89.4 -> 90.4, DUC2 93.9 -> 93.1No clear effect

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