AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAM

Xu Wang, Boyao Han, Xiaojun Chen, Ying Liu, Ruihui Li

AAAI 2026 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 2 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 progressive pose optimization (GICP+ORB+BA) over GICP only (ablation)PointSLAM++ · TUM-RGBDATE RMSE: 17.33 -> 1.08Improved
add progressive pose optimization (ablation)PointSLAM++ · TUM-RGBDPSNR: 21.47 -> 26.16Improved
add neural Gaussian representation (ablation)PointSLAM++ · TUM-RGBDPSNR: 24.06 -> 25.36Improved
add view-dependent compensation (ablation)PointSLAM++ · TUM-RGBDPSNR: 25.36 -> 26.16Improved
add view-dependent compensation (ablation)PointSLAM++ · TUM-RGBDATE RMSE: 1.10 -> 1.08No clear effect
use PointSLAM++ instead of GS-ICP SLAM on noisy-depth dataPointSLAM++ · ScanNet++PSNR: 14.94 -> 26.51Improved
PointSLAM++ vs GS-ICP SLAM tracking on clean-depth ReplicaPointSLAM++ · ReplicaATE RMSE: 0.16 -> 0.19No clear effect
PointSLAM++ vs SplaTAM on TUM-RGBD renderingPointSLAM++ · TUM-RGBDSSIM: 0.897 -> 0.885Hurt
PointSLAM++ vs GS-ICP SLAM on efficiencyPointSLAM++ · ScanNet++GPU memory (GB): 9.62 -> 10.11Hurt

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