AI Paper Atlas

Research map / 3D vision / Depth and stereo

InLoc: Indoor Visual Localization With Dense Matching and View Synthesis

Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, Akihiko Torii

CVPR 2018 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 464 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
Use InLoc's dense matching and view-synthesis pipeline instead of direct 2D-3D matchingIndoor visual localization · InLoc, 0.50m and 10° thresholdcorrectly localized queries (%): 15.8 -> 56.5Improved
Use dense CNN matching for pose estimation instead of sparse local-feature matching (ablation)NetVLAD retrieval · InLoclocalization rate: about 15%Improved
Add pose verification using virtual view synthesis (ablation)Top-10 candidate poses · InLocfraction correctly localized within 1.5m: 13% or moreImproved
Binarize intermediate CNN features rather than retaining float descriptors (ablation)Dense pose estimation · InLoc, 0.5m thresholdlocalization performance: less than 1%Hurt
Use NetVLAD retrieval rather than Disloc retrievalIndoor localization before SparsePE re-ranking · InLoc, 0.5m thresholdlocalization accuracy: 5.8%Improved
Replace SparsePE with DensePE while retaining NetVLAD retrieval (ablation)Indoor localization · Matterport3D (90 buildings)median positional and angular error: 0.44, 4.70° -> 0.23, 2.53°Improved
Add DensePE to NetVLAD + SparsePE (ablation)Indoor localization · 7 Scenesmedian positional and angular errorImproved

Later papers that compared with this method

3 later accepted papers report InLoc as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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