AI Paper Atlas

Research map / 3D vision / Gaussian splatting

QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization

Yueh-Cheng Liu, Lukas Höllein, Matthias Nießner, Angela Dai

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 9 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 the learned initializer network to the optimizer-only pipeline (ablation)QuickSplat · ScanNet++Abs err: 0.1332 -> 0.0581Improved
predict full 2DGS attributes in initializer instead of occupancy only (ablation)QuickSplat · ScanNet++Abs err: 0.0897 -> 0.0581Improved
add the learned densifier network (ablation)QuickSplat · ScanNet++Abs err: 0.0581 -> 0.0578Improved
initializer predicts more Gaussian attributes (color only to color, opacity, scales, rotation) (ablation)QuickSplat initializer · ScanNet++Abs err: 0.0627 -> 0.0578Improved
add 2000 SGD refinement steps after learned optimizationQuickSplat · ScanNet++Acc (2cm): 0.5263 -> 0.5783Improved
use learned optimizer and densifier instead of 2DGS optimization and densification with same initializer (ablation)QuickSplat · ScanNet++Acc (2cm): Acc (2cm) 0.4796 -> 0.5263; Abs err 0.0668 -> 0.0732Mixed
use QuickSplat initializer in SAGS instead of SfM initializationSAGS · ScanNet++Abs err: 0.1292 -> 0.0692Improved
increase learned optimizer steps from T=0 to T=5 (ablation)QuickSplat · ScanNet++Abs err: 0.0921 -> 0.0732Improved
increase learned optimizer steps from T=0 to T=5 (ablation)QuickSplat · ScanNet++Chamfer: 0.1478 -> 0.1461No clear effect
replace 2DGS with QuickSplat on unseen ARKitScenes without fine-tuningQuickSplat · ARKitScenes (5 scenes)Abs err: 0.6978 -> 0.1775Improved

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