AI Paper Atlas

Research map / 3D vision / Depth and stereo

Is This the Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization

Hajime Taira, Ignacio Rocco, Jiri Sedlar, Masatoshi Okutomi, Josef Sivic, Tomas Pajdla, Torsten Sattler, Akihiko Torii

ICCV 2019 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 51 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 scan-graph (multiple scans) view synthesisDensePV · InLocpose accuracy (%) at [0.50, 5]: 55.6 -> 59.0Improved
add scan-graph view synthesisDensePV · InLocpose accuracy (%) at [2.00, 10]: 74.2 -> 71.4Hurt
add semantic masking (+S) to dense pose verificationDensePV · InLoc (w/o scan-graph)pose accuracy (%) at [0.50, 5]: 55.6 -> 57.8Improved
add semantic masking (+S) with scan-graphDensePV · InLoc (w/ scan-graph)pose accuracy (%) at [0.25, 5]: 39.8 -> 41.3Improved
add surface-normal consistency to appearance (DensePNV)DensePV · InLoc (w/o scan-graph)pose accuracy (%) at [2.00, 10]: 74.2 -> 76.6Improved
add surface-normal consistency with scan-graphDensePV · InLoc (w/ scan-graph)pose accuracy (%) at [0.50, 5]: 59.0 -> 60.5Improved
add semantics on top of normals with scan-graph (DensePNV+S)DensePNV · InLoc (w/ scan-graph)pose accuracy (%) at [2.00, 10]: 75.4 -> 75.1No clear effect
use normals only without appearance (DenseNV)DensePE · InLoc (w/o scan-graph)pose accuracy (%) at [2.00, 10]: 61.1 -> 62.9No clear effect
train pose verification network on random perturbed views vs DPE-selected views (ablation)TrainPV · InLocpose accuracy (%) at [2.00, 10]: 76.3 -> 76.3No clear effect
add trainable verification (TrainPV random)DensePV · InLocpose accuracy (%) at [2.00, 10]: 74.2 -> 76.3Improved
add image cropping before normal estimation (ablation)DensePNV · InLocpose accuracy (%) at [1.00, 10]: 72.3 -> 71.7Hurt
add image cropping before normal estimation (ablation)DenseNV · InLocpose accuracy (%) at [0.25, 5]: 32.2 -> 29.5Hurt

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