AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Instant Uncertainty Calibration of NeRFs Using a Meta-Calibrator

Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 1 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
apply meta-calibrator to FlipNeRF uncertainties vs DANEFlipNeRF · LLFF 3-viewcalibration error: 0.0441 -> 0.0026Improved
apply meta-calibrator to FlipNeRF uncertainties vs DANEFlipNeRF · LLFF 3-viewNLL: 3.75 -> -0.68Improved
meta-calibrator vs DANE M=10 on standard LLFF uncertainty benchmarkFlipNeRF · LLFF 4-12 viewsNLL: -0.47 -> -1.67Improved
calibrate with held-out-free meta-calibrator vs holding out one view of Horns (ablation)NeRF calibration · LLFF HornsPSNR: 17% PSNR reduction when holding out one imageImproved
fit calibrator on training set instead of held-out data (ablation)Kuleshov recalibration · LLFFcalibration errorHurt
predict low-dimensional PCA coefficients instead of 384-dim discretized curve (ablation)meta-calibrator · LLFF Ferncalibration prediction qualityImproved
use calibrated instead of uncalibrated uncertainties for ray selectionnext-best view planning · DTU 15 scenesPSNRImproved
increase ray samples for FlipNeRF mixture up to 128 (ablation)FlipNeRF base uncertainties · LLFFcalibration errorImproved
interquartile range instead of variance for uncertainty metric (ablation)calibrated CDF · single pixel timingtime (s): 1.759 -> 0.008Improved

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