AI Paper Atlas

Research map / 3D vision / Gaussian splatting

VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM

Anh Thuan Tran, Jana Kosecka

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 3 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 uncertainty weighting to tracking (ablation)VarSplat · ScanNet (6 scenes) ablationATE RMSE (cm): 8.20 -> 7.63Improved
add uncertainty to loop detection (on top of tracking) (ablation)VarSplat · ScanNet (6 scenes) ablationATE RMSE (cm): 7.63 -> 7.49Improved
add uncertainty to registration (on top of tracking+loop) (ablation)VarSplat · ScanNet (6 scenes) ablationATE RMSE (cm): 7.49 -> 6.53Improved
freeze variance during tracking (ablation)VarSplat · ScanNet (6 scenes) ablationATE RMSE (cm): 7.55 -> 6.53Improved
add depth residuals to variance loss (ablation)VarSplat · ScanNet (6 scenes) ablationATE RMSE (cm): 7.17 -> 6.53Improved
use squared L2 instead of L1 for variance loss (ablation)VarSplat · ScanNet (6 scenes) ablationATE RMSE (cm): 7.38 -> 6.53Improved
VarSplat instead of LoopSplat on ScanNet++VarSplat · ScanNet++ trackingATE RMSE (cm): 2.05 -> 1.69Improved
VarSplat instead of LoopSplat on ReplicaVarSplat · Replica trackingATE RMSE (cm): 0.26 -> 0.23Improved
VarSplat instead of LoopSplat on Replica reconstructionVarSplat · Replica reconstructionDepth L1 / F1: F1 90.4 -> 90.2; Depth L1 0.51 -> 0.50No clear effect
VarSplat instead of Gaussian-SLAM on renderingVarSplat · Replica rendering PSNRPSNR: 42.08 -> 37.15Hurt
VarSplat instead of LoopSplat on ScanNet renderingVarSplat · ScanNet renderingPSNR: 24.92 -> 24.92No clear effect
add variance learning and renderingVarSplat · runtime on Replica/Room0mapping time per frame (s): LoopSplat 1.9 vs 1.2 s mapping/frameHurt

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