AI Paper Atlas

Research map / 3D vision / Depth and stereo

MeshVPR: Citywide Visual Place Recognition Using 3D Meshes

Gabriele Berton, Lorenz Junglas, Riccardo Zaccone, Thomas Pollok, Barbara Caputo, Carlo Masone

ECCV 2024 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 9 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 a synthetic mesh-rendered database instead of a real-image databaseSALAD · San FranciscoRecall@1: 96.3 -> 76.9Hurt
add MeshVPR features alignment to SALAD on synthetic databaseSALAD · Synt-BerlinRecall@1: 69.8 -> 82.0Improved
add MeshVPR features alignment to EigenPlaces on synthetic databaseEigenPlaces · Synt-MelbourneRecall@1: 26.7 -> 47.6Improved
add MeshVPR features alignment to Conv-AP on synthetic databaseConv-AP · Synt-ParisRecall@1: 34.3 -> 35.4No clear effect
add MeshVPR features alignment to EigenPlaces on synthetic databaseEigenPlaces · Synt-ParisRecall@1: 44.8 -> 48.5Improved
use high-quality mesh instead of low-quality mesh for alignment and test (ablation)SALAD + MeshVPR · San FranciscoRecall@1: 76.1 -> 88.8Improved
train alignment on HQ mesh and test on LQ database instead of training on LQ (ablation)MixVPR + MeshVPR · San Francisco LQ DBRecall@1: 59.7 -> 53.0Hurt
use features alignment with two models instead of metric-learning fine-tuning on mixed real and synthetic data (ablation)EigenPlaces · Synt-BerlinRecall@1: 40.4 -> 67.1Improved
increase alignment training set from 100k to 9.2M image pairs (ablation)MeshVPR · Synt-BerlinRecall@1: 81.2 -> 82.0No clear effect
increase alignment training set from 10k to 100k image pairs (ablation)MeshVPR · Synt-ParisRecall@1: 59.3 -> 61.2Improved
add MeshVPR to SALAD on synthetic San Francisco databaseSALAD · San FranciscoRecall@1: 76.9 -> 88.8Improved

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