AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MEGS^{2}: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning

Jiarui Chen, Yikeng Chen, Yingshuang Zou, Ye Huang, Peng Wang, Yuan Liu, Yujing Sun, Wenping Wang

ICLR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 6 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 soft (ADMM-style) pruning instead of hard pruning (ablation)MEGS2 · Mip-NeRF360PSNR: 27.23 -> 27.54Improved
use soft pruning instead of hard pruning (ablation)MEGS2 · Mip-NeRF360rendering VRAM (MB): 288 -> 265Improved
jointly optimize primitive and lobe pruning (unified) instead of sequential (ablation)MEGS2 · Mip-NeRF360PSNR: 27.33 -> 27.54Improved
jointly optimize unified instead of sequential (ablation)MEGS2 · Mip-NeRF360rendering VRAM (MB): 328 -> 265Improved
add color compensation after lobe removal (ablation)MEGS2 · Mip-NeRF360PSNR: 27.46 -> 27.54Improved
combine GaussianSpa with Reduced3DGS SH pruning (ablation)GaussianSpa · Mip-NeRF360PSNR: 27.54 -> 26.05Hurt
replace SH with SG in GaussianSpa (without unified pruning) (ablation)GaussianSpa · Mip-NeRF360PSNR: 27.01 -> 27.54Improved
use arbitrarily oriented SG lobes instead of fixed orthogonal axes (ablation)MEGS2 · Mip-NeRF360PSNR: about 0.6 dB drop for fixed-axisImproved
replace SH with arbitrarily oriented SG color (ablation)3DGS · Mip-NeRF360quality-VRAM trade-offImproved
MEGS2 vs GaussianSpa on rendering memoryMEGS2 HQ · Mip-NeRF360rendering VRAM (MB): 448 -> 265Improved
MEGS2 vs 3DGS on DeepBlending qualityMEGS2 HQ · DeepBlendingPSNR: 29.71 -> 30.17Improved
MEGS2 vs 3DGS on Tanks&Temples PSNRMEGS2 HQ · Tanks&TemplesPSNR: 23.68 -> 23.45Hurt

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