AI Paper Atlas

Research map / 3D vision / Depth and stereo

ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation

Jiahui Huang, Sheng Yang, Zishuo Zhao, Yu-Kun Lai, Shi-Min Hu

ICCV 2019 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 84 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 noise-aware (Mahalanobis, weighted) motion distance (ablation)ClusterSLAM · Synthetic indoor sequencesRMSE (m): 1.21 -> 0.44Improved
add noise-aware (Mahalanobis, weighted) motion distance (ablation)ClusterSLAM · Synthetic outdoor sequencesclustering accuracy (%): 86.51 -> 94.15Improved
add image-space prior term to motion distance (ablation)ClusterSLAM · Synthetic indoor sequencesclustering accuracy (%): 76.16 -> 91.54Improved
add image-space prior term to motion distance (ablation)ClusterSLAM · Synthetic outdoor sequencesRMSE (m): 9.56 -> 0.63Improved
use noise-aware ICP instead of point-to-point ICP for cluster initialization (ablation)ClusterSLAM · Synthetic outdoor sequencesRMSE (m): 8.54 -> 0.94Improved
use noise-aware ICP instead of point-to-point ICP for cluster initialization (ablation)ClusterSLAM · Synthetic indoor sequencesRMSE (m): 0.22 -> 0.12Improved
use noise-aware ICP instead of point-to-point ICP (ablation)ClusterSLAM · Synthetic outdoor sequencesinitialization time (ms): 0.01 -> 0.12Hurt
use decoupled instead of fully-coupled optimization (ablation)ClusterSLAM · Synthetic outdoor sequencesRMSE (m): 0.73 -> 0.12Improved
use decoupled instead of fully-coupled optimization (ablation)ClusterSLAM · Synthetic indoor sequencesRMSE (m): 0.034 -> 0.047Hurt
use decoupled instead of semi-decoupled optimization (ablation)ClusterSLAM · Synthetic indoor sequencestime per iteration (s): 1.04 -> 0.57Improved
use hierarchical agglomerative clustering instead of affinity propagation or spectral clustering (ablation)ClusterSLAM · Motion distance matrix 260x260running time: 13ms -> 6.3ms (AP), 180ms -> 6.3ms (SC)Improved
use smaller chunk sizes (30 to 300 range) (ablation)ClusterSLAM · CARLA long sequencesbeta VI and clustering timeMixed

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