AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

Chen Zhao, Xuan Wang, Tong Zhang, Saqib Javed, Mathieu Salzmann

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 14 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
use uncertainty-aware perturbation instead of random perturbation of all Gaussians (ablation)SE-GS · LLFF 3-view, 2000 iterationsPSNR: 18.63 -> 20.34Improved
use uncertainty-aware perturbation instead of gradient-aware perturbation (ablation)SE-GS · LLFF 3-view, 2000 iterationsPSNR: 19.18 -> 20.34Improved
add self-ensembling to 3DGS (3 views)3DGS · LLFF 3-viewPSNR: 19.22 -> 20.79Improved
add self-ensembling to 3DGS (3 views)3DGS · DTU 3-viewPSNR: 17.67 -> 19.24Improved
add self-ensembling to 3DGS (10 views)3DGS · MVImgNet 10-viewPSNR: 31.82 -> 32.68Improved
train more 3DGS models in CoR-GS (2 to 8) (ablation)CoR-GS · LLFF 3-viewPSNR: peak at 6 modelsMixed
perturb the Delta-model every 100 iterations instead of 500 (ablation)SE-GS · LLFF 3-viewPSNRHurt
perturb every 900 iterations instead of 500 (ablation)SE-GS · LLFF 3-viewPSNRHurt
use strong noise level omega 0.3 or 0.2 instead of decayed 0.08 to 0.02 (ablation)SE-GS · LLFF 3-viewPSNRHurt
use small fixed omega 0.01 instead of decayed omega (ablation)SE-GS · LLFF 3-viewPSNRHurt
use FSGS depth supervision instead of vanilla 3DGS (9 views)FSGS · LLFF 9-viewPSNR: 25.44 -> 25.31Hurt

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