AI Paper Atlas

Research map / 3D vision / Gaussian splatting

SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation

Zixuan Pan, Kaiyuan Tang, Jun Xia, Yifan Qin, Lin Gu, Chaoli Wang, Jianxu Chen, Yiyu Shi

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 2 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 multi-scale (coarse-to-fine) fitting with 3 pyramid levels (ablation)SGI · FGF2optimization time (min): 71.59 -> 48.43Improved
add multi-scale (coarse-to-fine) fitting with 3 pyramid levels (ablation)SGI · FGF2PSNR: 30.58 -> 31.24Improved
increase pyramid levels from 3 to 4 (ablation)SGI · ICBPSNR: 35.27 -> 33.78Hurt
add entropy coding with context model (lambda 0.001 vs 0) (ablation)SGI · FGF2model size (MB): 104.08 -> 16.33Improved
add entropy coding with context model (lambda 0.001 vs 0) (ablation)SGI · FGF2PSNR: 32.36 -> 31.24Hurt
increase lambda from 0.001 to 0.003 (ablation)SGI · ICBPSNR: 35.27 -> 33.51Hurt
increase Gaussians per seed K from 10 to 20 (ablation)SGI · FGF2model size (MB): 16.33 -> 14.83Improved
increase Gaussians per seed K from 10 to 20 (ablation)SGI · FGF2PSNR: 31.24 -> 30.62Hurt
decrease Gaussians per seed K from 10 to 5 (ablation)SGI · FGF2model size (MB): 16.33 -> 18.48Hurt
use seed-based 2D neural Gaussians alone without entropy coding (ablation)unstructured 2D Gaussians (LIG) · FGF2 / ICBmodel size: about 3% reductionNo clear effect
use SGI instead of GaussianImage at 3.5M Gaussians2D Gaussian image representation · FGF2PSNR: 27.30 -> 31.24Improved
use SGI low-rate instead of I-NGP on STimageimage representation · STimagePSNR: 35.57 -> 33.96Hurt

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