AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MBA-SLAM: Motion Blur Aware Dense Visual SLAM With Radiance Fields Representation

Peng Wang, Lingzhe Zhao, Yin Zhang, Shiyu Zhao, Peidong Liu

TPAMI 2025 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 10 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 3D Gaussian Splatting mapper instead of tri-plane NeRF mapperMBA-SLAM · ArchViz (synthetic blur)ATE RMSE avg (cm): 1.69 -> 0.84Improved
use 3D Gaussian Splatting mapper instead of tri-plane NeRF mapperMBA-SLAM · ArchViz (synthetic blur)PSNR avg: 25.08 -> 28.82Improved
use 3D Gaussian Splatting mapper instead of tri-plane NeRF mapperMBA-SLAM · Replica (sharp)PSNR avg: 30.85 -> 36.98Improved
use 3D Gaussian Splatting mapper instead of tri-plane NeRF mapperMBA-SLAM · Replica (sharp)FPS: 2.75 -> 497.63Improved
replace vanilla NeRF with tri-plane representationBAD-NeRF based mapper · training efficiencytraining speed: 100 timesImproved
blur-aware tracker plus mapper vs MonoGSMBA-SLAM (Ours-GS) · ArchViz (synthetic blur)ATE RMSE avg (cm): 14.42 -> 0.84Improved
blur-aware tracker plus mapper vs Photo-SLAM on real blurMBA-SLAM (Ours-GS) · Realsense blurred sequences (seq1-3)ATE RMSE avg (cm): 35.81 -> 5.87Improved
blur-aware NeRF tracker vs ESLAM on real blurMBA-SLAM (Ours-NeRF) · TUM/ScanNet blurred sequences (pub1-3)ATE RMSE avg (cm): 2.81 -> 2.34Improved
MBA-SLAM NeRF vs Point-SLAM on sharp Replica trackingMBA-SLAM (Ours-NeRF) · Replica (sharp)ATE RMSE avg (cm): 0.54 -> 0.41Improved
MBA-SLAM NeRF vs Point-SLAM on sharp Replica renderingMBA-SLAM (Ours-NeRF) · Replica (sharp)PSNR avg: 35.05 -> 30.85Hurt
MBA-SLAM GS vs RTG-SLAM on sharp Replica trackingMBA-SLAM (Ours-GS) · Replica (sharp)ATE RMSE avg (cm): 0.18 -> 0.35Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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