AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting

Xianben Yang, Tao Wang, Yuxuan Li, Yi Jin, Haibin Ling

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 1 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 GSDO (graph-based spatial distribution optimization) after pruningLightGaussian · Mip-NeRF 360 (all 9 scenes)PSNR: 27.35 -> 27.75Improved
add GSDO after pruningMaskGaussian · Tanks & Temples (21 scenes)PSNR: 24.16 -> 24.63Improved
add GSDO after pruningLightGaussian · Tanks & Temples (21 scenes)PSNR: 23.16 -> 23.97Improved
add opacity-aware pruning to ELBO densification (ablation)3DGS · Mip-NeRF 360 (all 9 scenes)PSNR: 27.73 -> 26.79Hurt
add ELBO adaptive densification (ablation)3DGS · Mip-NeRF 360 (all 9 scenes)Number of Gaussians (M): 3.12 -> 2.82Improved
add ELBO adaptive densification (ablation)3DGS · Tanks & Temples (21 scenes)PSNR: 24.19 -> 24.40Improved
increase training iterations after pruning (ablation)GS^2 pruned model · Mip-NeRF 360 (all 9 scenes)PSNR: 26.79 -> 26.98No clear effect
add local smoothness loss and spatial optimization (Lsmt) (ablation)pruned 3DGS · Mip-NeRF 360 (all 9 scenes)PSNR: 26.98 -> 27.53Improved
add full GSDO (Lcet and graph encoder) on top of Lsmt (ablation)pruned 3DGS · Tanks & Temples (21 scenes)PSNR: 24.49 -> 24.90Improved
increase pruning interval from 100 to 400 iterations (ablation)GS^2 · Mip-NeRF 360 (all 9 scenes)PSNR: 27.74 -> 27.60No clear effect
add GSDO module to ADP (ablation)GS^2 · Tanks & Temples (21 scenes)Train time (min): 10 -> 16Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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