AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis

Chamuditha Jayanga Ahangama Galappaththige, Thomas Gottwald, Peter Stehr, Edgar Heinert, Niko Suenderhauf, Dimity Miller, Matthias Rottmann

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 5 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 view-dependence via SH degree 1 (ablation)uncertainty channel · Mip-NeRF360 UE (novel views)AUSE DSSIM: 0.310 -> 0.245Improved
raise SH degree from 2 to 3 (ablation)uncertainty channel · Mip-NeRF360 UE (novel views)AUSE DSSIM: 0.218 -> 0.214Improved
raise SH degree from 1 to 3 (ablation)uncertainty channel · Mip-NeRF360 UE (novel views)Pearson DSSIM: 0.498 -> 0.547Improved
add Bayesian-inspired regularization in dense capture (ablation)uncertainty channel · Mip-NeRF360 dense captureAUSENo clear effect
add Bayesian-inspired regularization with 4 training views (ablation)uncertainty channel · Mip-NeRF360 sparse (4 views)AUSEMixed
increase regularization weight to 0.16-0.32 for L1 error (ablation)uncertainty channel · Mip-NeRF360 sparse (4 views)AUSE L1Improved
increase regularization weight to 10.24 for DSSIM error (ablation)uncertainty channel · Mip-NeRF360 sparse (4 views)AUSE DSSIMImproved
replace Var3DGS with oursuncertainty estimation · Mip-NeRF360 UE (novel views)AUSE DSSIM: 0.495 -> 0.214Improved
replace FisherRF with oursuncertainty estimation · Mip-NeRF360 UE (novel views)Pearson DSSIM: 0.009 -> 0.547Improved
use predicted uncertainty to guide view selection instead of FisherRFactive view selection · Active view selection, Mip-NeRF360PSNR: 20.266 -> 20.676Improved
attenuate change map with uncertaintyFeature Diff. · Pose-agnostic SCD, PASLCDmIoU: 0.278 -> 0.359Improved
attenuate change map with uncertaintyMV3DCD-ZS · Pose-agnostic SCD, PASLCDmIoU: 0.382 -> 0.439Improved

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