AI Paper Atlas

Research map / Point clouds / Point cloud classification

Point-SLAM: Dense Neural Point Cloud-based SLAM

Erik Sandström, Yue Li, Luc Van Gool, Martin R. Oswald

ICCV 2023 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 278 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 non-linear preprocessing network F_theta on color features (ablation)Point-SLAM · Replica Room 0PSNR (dB): 27.41 -> 32.09Improved
add F_theta when tracking errors are highPoint-SLAM · TUM-RGBD, ScanNetrendering qualityNo clear effect
add RGB to tracking (ablation)Point-SLAM · Replica Room 0ATE RMSE (cm): 0.67 -> 0.36Improved
add RGB to mapping (ablation)Point-SLAM · Replica Room 0F1 (%): 91.37 -> 91.49No clear effect
increase upper search radius r_u (more compression)Point-SLAM · Replica Room 0ATE RMSE, depth L1, PSNRMixed
use adaptive neural point cloud instead of NICE-SLAM voxel griddense neural RGBD SLAM · Replica renderingPSNR (dB): 24.42 -> 35.17Improved
use Point-SLAM on ScanNet instead of NICE-SLAMPoint-SLAM · ScanNet trackingATE RMSE (cm): 10.70 -> 12.19Hurt
use Point-SLAM instead of traditional sparse trackersTUM-RGBD tracking · TUM-RGBDATE RMSE (cm): ORB-SLAM2 1.98 vs 8.92Hurt

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