AI Paper Atlas

Research map / 3D vision / Depth and stereo

On the Limits of Pseudo Ground Truth in Visual Camera Re-Localisation

Eric Brachmann, Martin Humenberger, Carsten Rother, Torsten Sattler

ICCV 2021 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 68 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
switch reference pGT from original SLAM to SfMActive Search · 7Scenes averageimages localised within 5cm,5deg (%): 68.7 -> 98.5Improved
switch reference pGT from original SLAM to SfMActive Search · 7Scenes Pumpkinimages localised within 5cm,5deg (%): 34.1 -> 99.6Improved
switch reference pGT from original SLAM to SfMActive Search · 7Scenes Red Kitchenimages localised within 5cm,5deg (%): 45.1 -> 99.8Improved
switch reference pGT from original SLAM to SfMDSAC* (+D) · 7Scenes averageimages localised within 5cm,5deg (%): 94.7 -> 95.3 (rank first to last)Hurt
switch reference pGT from original SLAM to SfMDenseVLAD+R2D2 (+D) · 7Scenes averageimages localised within 5cm,5deg (%): 80.2 -> 92.9Mixed
switch reference pGT from original SLAM to SfMhLoc · 7Scenes averageimages localised within 5cm,5deg (%): 76.8 -> 95.7Improved
switch reference pGT from original SLAM to SfMDSAC* · 7Scenes averageimages localised within 5cm,5deg (%): 82.9 -> 97.8Improved
use +BA refined test poses instead of original posesActive Search · 7Scenes averageimages localised within 5cm,5deg (%): 68.7 -> 79.5Improved
use +BA refined test poses instead of original posesDSAC* (+D) · 7Scenes averageimages localised within 5cm,5deg (%): 94.7 -> 93.2Hurt
use +BA refined test poses instead of original posesDenseVLAD+R2D2 (+D) · 7Scenes averageimages localised within 5cm,5deg (%): 80.2 -> 85.0Improved
add depth input (+D) to DSAC*DSAC* · 7Scenes (original SLAM pGT)images localised within 5cm,5deg (%): 82.9 -> 94.7Improved
add depth input (+D) to DSAC*DSAC* · 7Scenes (SfM pGT)images localised within 5cm,5deg (%): 97.8 -> 95.3Hurt

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