AI Paper Atlas

Research map / 3D vision / Gaussian splatting

SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM

Mingrui Li, Shuhong Liu, Heng Zhou, Guohao Zhu, Na Cheng, Tianchen Deng, Hongyu Wang

ECCV 2024 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 152 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 semantic map supervision to multi-channel optimization (ablation)SGS-SLAM · ScanNet scene0000_00ATE RMSE (cm): 13.81 -> 11.26Improved
add depth supervision (ablation)SGS-SLAM · ScanNet scene0000_00Depth L1 (cm): 47.66 -> 6.18Improved
add color image supervision (ablation)SGS-SLAM · ScanNet scene0000_00ATE RMSE (cm): 24.59 -> 11.26Improved
add silhouette threshold in tracking (ablation)SGS-SLAM · ScanNet scene0000_00ATE RMSE (cm): 357.48 -> 11.26Improved
add geometric overlap threshold in keyframe selection (ablation)SGS-SLAM · ScanNet scene0000ATE RMSE (cm): 15.55 -> 11.26Improved
add semantic threshold in keyframe selection (ablation)SGS-SLAM · ScanNet scene0000PSNR (dB): 17.84 -> 19.47Improved
add uncertainty weighting of keyframes (ablation)SGS-SLAM · ScanNet scene0000PSNR (dB): 18.72 -> 19.47Improved
use Gaussian splatting with semantic channel instead of NeRF-based semantic SLAMSGS-SLAM · Replica (4 scenes)avg mIoU (%): 87.41 -> 92.72Improved
add semantic channel and keyframe selection to Gaussian SLAM (vs SplaTAM)SGS-SLAM · Replica (8 scenes avg)Depth L1 (cm): 0.525 -> 0.356Improved
SGS-SLAM vs SplaTAM on runtimeSGS-SLAM · Replica (8 scenes avg)SLAM FPS: 2.26 -> 2.11Hurt
SGS-SLAM vs ESLAM on ScanNet trackingSGS-SLAM · ScanNet (6 scenes)ATE RMSE avg (cm): 7.88 -> 9.87Hurt
Gaussian representation vs ESLAM on large-motion ScanNet++SGS-SLAM · ScanNet++ (2 scenes)ATE RMSE avg (cm): 170.06 -> 1.62Improved

Later papers that compared with this method

2 later accepted papers report SGS-SLAM as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 5 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