AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting

Qinzheng Zhou, Zaychik Liu, Lijing Lu, Zhihang Li

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

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 confidence-guided hierarchical aggregation (ablation)3DGS (CAGS) · ablation, original ResPSNR: 15.32 -> 18.45Improved
add multi-scale pseudo-view regularization (ablation)3DGS (CAGS) · ablation, original ResPSNR: 15.32 -> 16.43Improved
add multi-scale regularization on top of hierarchical aggregation (ablation)CAGS · ablation, original ResPSNR: 18.45 -> 18.83Improved
add multi-scale regularization on top of hierarchical aggregation (ablation)CAGS · ablation, 1/2 ResPSNR: 19.10 -> 19.50Improved
add hierarchical aggregation on top of multi-scale regularization (ablation)CAGS · ablation, original ResPSNR: 16.43 -> 18.83Improved
plug CAGS into DropGaussianDropGaussian · DTU original ResPSNR: 17.45 -> 19.13Improved
plug CAGS into FSGSFSGS · DTU original ResPSNR: 17.32 -> 18.67Improved
plug CAGS into CoR-GSCoR-GS · DTU original ResPSNR: 17.51 -> 19.25Improved
use CAGS instead of NexusGS at original resolutionsparse-view 3DGS · LLFF original ResPSNR: 16.12 -> 18.85Improved
use CAGS instead of NexusGS at 1/4 resolutionsparse-view 3DGS · LLFF 1/4 ResPSNR: 20.29 -> 20.62Improved
lower input resolution (full to 1/8) in plain 3DGS3DGS · empirical study (qualitative)visual qualityMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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