AI Paper Atlas

Research map / 3D vision / Gaussian splatting

PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage

Thomas Gottwald, Edgar Heinert, Peter Stehr, Chamuditha Jayanga Galappaththige, Matthias Rottmann

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 4 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 PRIMU primitive-based uncertainty feature maps with gradient boosting regression instead of prior GS UE methods3DGS · LF rendering error UEAUSE: 0.753 (FisherRF) -> 0.291Improved
use PRIMU instead of BayesRays and FisherRF for depth UE3DGS · LF depth error UEAUSE: 0.173 (BayesRays) -> 0.115Improved
add direction-dependent coverage and error maps (ablation)PRIMU rendering UE · LF rendering error UEAUSE: 0.291 -> 0.286Improved
add direction-dependent coverage and error maps (ablation)PRIMU depth UE · LF depth error UEAUSE: 0.115 -> 0.118No clear effect
use gradient boosting instead of linear regression for the pixel-wise regressor (ablation)PRIMU · object-centric LF depth UEAUSE: 0.246 -> 0.071Improved
add a meta-regression stage to FisherRF (regression-based FisherRF) (ablation)FisherRF · LF rendering error UE, 1 viewAUSE: 0.878 -> 0.282Improved
train the regressor on more than one hold-out view (ablation)PRIMU · LF entire-scene rendering UEAUSE: 0.244 -> 0.222Improved
restrict training and evaluation to the central object (ablation)PRIMU · LF rendering error UEAUSE: 0.244 -> 0.072Improved
reduce 13 uncertainty feature maps to 9 (entire scene) or 6 (object-centric) (ablation)PRIMU · LF and TUM UEAUSE / Pearson: 0.244 -> 0.245 (LF entire-scene rendering AUSE, 9 maps)No clear effect
use PRIMU direction-dependent coverage map (max aggregation, no opacity) for active view selection3DGS AVS · MipNeRF360, 20 viewsPSNR: 20.392 (FisherRF) -> 20.721Improved
add FoV counter and max-aggregation coverage map without opacity (ablation)PRIMU depth UE · LF and TUM backward regressionPearson correlationImproved
include rendering-error-derived feature maps for depth UE (ablation)PRIMU depth UE · LF and TUM backward regressionPearson correlationNo clear effect

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