AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Complexity Aware Continuous Level of Details for Gaussian Splatting

Radu Beche, Raoul de Charette

NeurIPS 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies how to allocate capacity in a single 3D Gaussian Splatting set so that prefix truncations under varying compute budgets remain effective, motivated by image complexity correlating with reconstruction error.

Problem

A single Gaussian set must remain effective when truncated to a prefix of primitives under varying compute budgets, raising how capacity should be allocated as the budget decreases.

Approach

Observes that image complexity correlates with reconstruction error in both image and 3D Gaussian space, and that this structure degrades as budget decreases; the abstract is truncated so the specific method is not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add complexity-aware densification, importance score and variance loss to 3DGS-MCMC (ablation)3DGS-MCMC · MipNerf360 (7 scenes)AUC PSNR: 28.74 -> 29.09Improved
add complexity-aware importance score only (ablation)3DGS-MCMC · MipNerf360 (7 scenes)AUC PSNR: 28.74 -> 28.94Improved
add complexity-aware densification only (ablation)3DGS-MCMC · MipNerf360 (7 scenes)PSNR at 100% capacity: 29.55 -> 29.79Improved
add variance loss only (ablation)3DGS-MCMC · MipNerf360 (7 scenes)AUC SSIM: 0.855 -> 0.855No clear effect
add variance loss to densification alone (ablation)complexity densification · MipNerf360 (7 scenes)AUC PSNR: 28.81 -> 28.75Mixed
add variance loss on top of densification + score (ablation)KoalaGS · MipNerf360 (7 scenes)AUC PSNR: 28.99 -> 29.09Improved
use complexity dropout 0.2 instead of none (0) (ablation)complexity-biased relocation · Deep Blending (2 scenes)AUC PSNR: 29.00 -> 29.51Improved
use complexity dropout 0.2 instead of pure opacity sampling (1) (ablation)complexity-biased relocation · Tanks and Temples (2 scenes)AUC PSNR: 23.88 -> 24.02Improved
use high dropout rates 0.6 or 0.8 (ablation)complexity-biased relocation · Deep Blending / Tanks and TemplesAUC PSNR: 29.51 -> 28.94 (delta 0.6, DB)Hurt
rank primitives by opacity plus scale over complexity instead of opacity alone, with complexity-aware training3DGS-MCMC · MipNerf360 (7 scenes), 10% capacityPSNR: 20.58 -> 27.82Improved
use KoalaGS instead of MGS at 0.1% capacityprefix LoD · Tanks and Temples (2 scenes)PSNR: 12.10 -> 11.56Mixed
use KoalaGS ranking for progressive streaming vs MGSstreaming · Bonsai, 50 Mbpstime to 25 dB: 1.96 s -> 1.47 sImproved

Earlier methods this paper compares with

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