AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Scene Experts: Specializing in 3D Gaussian Splatting with Adaptive Decomposition

Xiaowen Fu, Yang Zhang, Yuhan Tang, Huazhong Zhang, Tianxing Zhao, Yuhang Guo, Yu Huang, Jinbao Wang

AAAI 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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
replace single MLP decoder with sparse MoE of 5 experts, Top-2 (ablation)MoE-GS · DeepBlendingPSNR: 30.37 -> 30.64Improved
replace single MLP decoder with MoE (ablation)MoE-GS · Tanks&TemplesPSNR: 24.30 -> 24.61Improved
add dense-to-sparse curriculum learning (ablation)MoE-GS · DeepBlendingPSNR: 30.47 -> 30.64Improved
add load balancing loss (ablation)MoE-GS · DeepBlendingPSNR: 30.53 -> 30.64Improved
add load balancing loss (ablation)MoE-GS · Quebec (BungeeNeRF), covariance expertanchor share of busiest expert: 73.1% -> 33.7%Improved
add opacity-aware regularization loss (ablation)MoE-GS · DeepBlendingPSNR: 30.52 -> 30.64Improved
add opacity-aware regularization loss (ablation)MoE-GS · DeepBlendingmodel size (MB): 58.6 -> 55.4Improved
add opacity-aware regularization to Scaffold-GS (ablation)MoE-GS · MipNeRF360Gaussian activation ratio: 36.9 -> 63.1Improved
increase number of experts from 2 to 5 (ablation)MoE-GS · DeepBlendingPSNRImproved
use Top-1 routing instead of Top-2 (ablation)MoE-GS · DeepBlendingPSNRHurt
use dense routing instead of Top-2 (ablation)MoE-GS · DeepBlendingtraining timeMixed
use anchor positions as router input (ablation)MoE-GS · DeepBlendingPSNRNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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