AI Paper Atlas

Research map / 3D vision / Depth and stereo

LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System

Hongbeen Park, Minjeong Park, Giljoo Nam, Jinkyu Kim

ECCV 2024 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 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
replace tri-plane representation with CP geometry plus Six-axis appearance decompositionESLAM · Replica/ScanNet/TUM efficiencytotal parameters: 87.3%-90.1% fewer parameters than ESLAMImproved
replace tri-plane representation with low-rank hybrid decompositionESLAM · TUM RGB-D fr1/deskframe processing time (s): 4.56 -> 1.22Improved
replace tri-plane representation with low-rank hybrid decompositionESLAM · ScanNet (6 scenes, average)ATE Mean (cm): 6.5 -> 6.1Improved
replace tri-plane representation with low-rank hybrid decomposition on clean synthetic dataESLAM · Replica room0 (clean depth)Depth L1 (cm): 1.18 -> 1.58Hurt
replace tri-plane representation with low-rank hybrid decomposition under noisy depth inputESLAM · Replica room0 (noisy depth)Depth L1 (cm): 3.22 -> 1.20Improved
replace tri-plane representation with low-rank hybrid decomposition on TUM fr3/officeESLAM · TUM RGB-D fr3/officeATE RMSE (cm): 2.42 -> 2.79Hurt
use CP decomposition for geometry and Six-axis decomposition for appearance rather than CP for both (ablation)LRSLAM · ScanNet ablationATE RMSEImproved
use CP or Six-axis decomposition instead of tri-plane (ablation)scene representation · ScanNet ablationparameter count: 4%-6% and 8%-12% fewer parameters than tri-planeImproved

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