AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Manifold-Aware Spectral Compaction: A Graph Signal Processing Perspective on Online Gaussian Reduction for 3DGS SLAM

Jiayi Tian, Jiaze Wang, Tian Xia, Wenzhe zhao, Pengju Ren

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 0 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 spectral MASC compaction instead of random subsampling (ablation)DROID-Splat at 40% retention · Replica (RGB-D, rho=40% ablation)PSNR: 28.15 -> 39.16Improved
use spectral MASC compaction instead of heuristic pruning (ablation)DROID-Splat at 40% retention · Replica (RGB-D, rho=40% ablation)PSNR: 35.20 -> 39.16Improved
use spectral clustering instead of Euclidean K-Means (ablation)DROID-Splat at 40% retention · Replica (RGB-D, rho=40% ablation)ATE (cm): 0.40 -> 0.33Improved
add appearance cues to graph weights (ablation)MASC · TUM RGB-D (rho=40%)PSNR: 19.45 -> 20.96Improved
add SKL divergence to graph weights (versus L2) (ablation)MASC · TUM RGB-D (rho=40%)PSNR: 19.85 -> 20.96Improved
use Wasserstein barycenter aggregation instead of simple mean (ablation)MASC · TUM RGB-D (rho=40%)ATE (cm): 1.45 -> 1.42Improved
use 1000 Nystrom landmarks instead of 100 (ablation)MASC · TUM RGB-D (rho=40%)PSNR: 18.20 -> 20.96Mixed
add MASC compaction (40% retention)DROID-Splat (RGB-D) · ReplicaGPU memory: 14.00 GB -> 5.00 GBImproved
add MASC compaction (40% retention)DROID-Splat (RGB-D) · ReplicaR-FPS: 145 -> 350Improved
add MASC compaction (40% retention)DROID-Splat (RGB-D) · ReplicaPSNR: 39.66 -> 39.16No clear effect
add MASC compaction (40% retention)Photo-SLAM · TUM RGB-D (average)ATE (cm): 1.32 -> 0.98Improved
add MASC compactionPhoto-SLAM (RGB-D) · ReplicaATE RMSE (cm): 0.60 -> 0.30Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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