AI Paper Atlas

Research map / 3D vision / Depth and stereo

GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction

Youmin Zhang, Fabio Tosi, Stefano Mattoccia, Matteo Poggi

ICCV 2023 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 184 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 top-ranked keyframe selection (largest pose change) on top of latest and stratified keyframes (ablation)GO-SLAM · Replicaavg F-score: 83.13 -> 85.56Improved
add stratified sampling to latest-only keyframe selection (ablation)GO-SLAM · Replicaavg F-score: 49.55 -> 83.13Improved
add depth loss to RGB loss (ablation)GO-SLAM · Replicaavg F-score: 34.64 -> 83.50Improved
add SDF loss and Eikonal loss to color and depth losses (ablation)GO-SLAM · Replicaavg F-score: 83.50 -> 85.56Improved
add loop closing to the DROID-SLAM VO baseline (ablation)GO-SLAM · ScanNet RGB-Davg ATE RMSE (cm): 11.59 -> 8.83Improved
add online full bundle adjustment (ablation)GO-SLAM · ScanNet RGB-Davg ATE RMSE (cm): 11.59 -> 7.11Improved
combine loop closing with full BA (ablation)GO-SLAM · ScanNet RGB-Davg ATE RMSE (cm): 7.11 -> 7.02Improved
skip 7/8 of RGB-D frames for 8x speedup (ablation)GO-SLAM · ScanNet / Replicaavg ATE RMSE (cm): 7.02 -> 7.28No clear effect
use GO-SLAM instead of DROID-SLAM with offline global BA on long monocular sequencesGO-SLAM · ScanNet monocularavg ATE RMSE (cm): 52.60 -> 17.59Improved
use GO-SLAM instead of DROID-SLAM on EuRoC stereoGO-SLAM · EuRoC stereoavg ATE RMSE (m): 0.024 vs 0.024No clear effect

Later papers that compared with this method

8 later accepted papers report GO-SLAM as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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