AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

RIO: 3D Object Instance Re-Localization in Changing Indoor Environments

Johanna Wald, Armen Avetisyan, Nassir Navab, Federico Tombari, Matthias Niessner

ICCV 2019 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 168 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 multi-scale network instead of single scale 120cm, both static (ablation)RIO · 3RScan keypoint matching (dynamic patches, 95% recall)F1: 74.17 -> 85.58Improved
use multi-scale network instead of single scale 120cm, both static (ablation)RIO · 3RScan keypoint matching (dynamic patches, 95% recall)Top-1: 3.94 -> 30.73Improved
add fine-tuning on dynamic patches (ablation)RIO-multiscale · 3RScan keypoint matching (dynamic patches, 95% recall)F1: 85.58 -> 94.37Improved
add fine-tuning on dynamic patches (ablation)RIO-multiscale · 3RScan keypoint matching (dynamic patches, 95% recall)Top-1: 30.73 -> 64.10Improved
add fine-tuning on dynamic patches (ablation)RIO-singlescale 120cm · 3RScan keypoint matching (dynamic patches, 95% recall)F1: 74.17 -> 78.71Improved
add larger context scale (120cm) to single 60cm scale input (ablation)RIO-singlescale (static) · 3RScan keypoint matching (dynamic patches, 95% recall)F1: 71.54 -> 74.17Improved
add fine-tuning on dynamic patches (ablation)RIO-multiscale · 3RScan object instance re-localization (test set)recall < 0.1m, 10deg (%): 9.92 -> 15.14Improved
add fine-tuning on dynamic patches (ablation)RIO-multiscale · 3RScan object instance re-localization (test set)recall < 0.2m, 20deg (%): 17.75 -> 23.76Improved
add fine-tuning on dynamic patches (ablation)RIO-multiscale · 3RScan object instance re-localization (test set)MRE [deg] at 0.1m, 10deg: 4.33 -> 4.75No clear effect
use RIO-multiscale (dynamic) instead of SHOThand-crafted descriptor · 3RScan object instance re-localization (test set)recall < 0.2m, 20deg (%): 12.27 -> 23.76Improved
use RIO-multiscale (dynamic) instead of 3DMatch trained on static patcheslearned descriptor · 3RScan object instance re-localization (test set)recall < 0.2m, 20deg (%): 13.05 -> 23.76Improved
use RIO-D instead of FPFH on bed / sofa objectsdescriptor · 3RScan object instance re-localization (test set)accuracy (%) bed / sofa: 56.52 -> 47.83Hurt

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