AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

ActiveNeRF: Learning Where to See with Uncertainty Estimation

Xuran Pan, Zihang Lai, Shiji Song, Gao Huang

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 133 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 uncertainty estimationNeRF · NeRF synthetic (10 images)PSNR: 28.04 -> 28.51Improved
add uncertainty estimationNeRF · NeRF synthetic (5 images)PSNR: 21.14 -> 23.23Improved
add uncertainty estimationNeRF · NeRF synthetic (all images)PSNR: 31.01 -> 30.45No clear effect
add uncertainty estimationNeRF · LLFF realistic (5 images)PSNR: 21.67 -> 22.03Improved
add uncertainty estimationNeRF · LLFF realistic (all images)PSNR: 26.50 -> 25.96No clear effect
use ActiveNeRF acquisition instead of random view capture (continuous learning)NeRF · NeRF synthetic (20 observations)PSNR: 24.25 -> 26.24Improved
use ActiveNeRF acquisition instead of furthest view sampling (continuous learning)NeRF · NeRF synthetic (20 observations)PSNR: 26.00 -> 26.24Improved
use ActiveNeRF acquisition instead of random view capture (continuous learning)NeRF · LLFF realistic (10 observations)PSNR: 18.49 -> 20.14Improved
use continuous learning instead of Bayesian estimationActiveNeRF · NeRF synthetic (20 observations)PSNR: 25.67 -> 26.24Improved
use Bayesian estimation instead of continuous learningActiveNeRF · NeRF synthetic (20 observations)time: 2.2h -> 30minImproved
add acquisition function over random selection (ablation)ActiveNeRF · NeRF synthetic (20 observations)PSNR: 24.77 -> 26.24Improved
add acquisition function over furthest view sampling (ablation)ActiveNeRF · NeRF synthetic (20 observations)PSNR: 26.05 -> 26.24Improved

Later papers that compared with this method

4 later accepted papers report ActiveNeRF as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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