AI Paper Atlas

Research map / 3D vision / Gaussian splatting

RGBD GS-ICP SLAM

Seongbo Ha, Jiung Yeon, Hyeonwoo Yu

ECCV 2024 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 111 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 plane scale regularization with ellipse regularization in G-ICP tracking (ablation)RGBD GS-ICP SLAM · TUM-RGBDATE RMSE avg (cm): 29.12 -> 2.37Improved
reuse G-ICP covariances to initialize new Gaussians instead of simple-knn scales (ablation)RGBD GS-ICP SLAM · ReplicaATE (cm): 8.893 -> 0.258Improved
divide new Gaussian scale by z^1.5 (scale aligning) (ablation)RGBD GS-ICP SLAM · ReplicaPSNR (dB): 33.21 -> 38.83Improved
use z^1.5 instead of z for scale normalization (ablation)RGBD GS-ICP SLAM · ReplicaPSNR (dB): 38.70 -> 38.83No clear effect
add mapping-only keyframes every 10 frames separate from tracking keyframes (ablation)RGBD GS-ICP SLAM · ReplicaATE (cm): 0.176 -> 0.157Improved
train mapping on random keyframes instead of the most recent keyframe (ablation)RGBD GS-ICP SLAM · ReplicaPSNR (dB): 26.85 -> 38.83Improved
add Gaussian densification during mapping (ablation)RGBD GS-ICP SLAM · ReplicaATE (cm): 0.157 -> 0.188Hurt
add Gaussian pruning during mapping (ablation)RGBD GS-ICP SLAM · ReplicaATE (cm): 0.159 -> 0.157No clear effect
limit tracking to 30 FPS instead of unlimited speedRGBD GS-ICP SLAM · ReplicaPSNR (dB): 35.93 -> 38.83Improved
use G-ICP coupled single-map tracking versus SplaTAM on TUM-RGBDRGBD GS-ICP SLAM · TUM-RGBDPSNR (dB): 23.46 -> 20.72Hurt

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