AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

FisherRF: Active View Selection and Mapping with Radiance Fields using Fisher Information

Wen Jiang, BOSHU LEI, Kostas Daniilidis

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 44 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
select views by Fisher Information EIG instead of random on 3D Gaussian Splatting3D Gaussian Splatting · Blender (sequential, 20 views)PSNR: 28.732 -> 29.525Improved
select views by EIG instead of ActiveNeRF variance selection3D Gaussian Splatting · Blender (sequential, 20 views)PSNR: 26.610 -> 29.525Improved
batch EIG selection instead of random3D Gaussian Splatting · Blender (batch of 4)PSNR: 27.135 -> 29.094Improved
EIG selection instead of random with only 10 views3D Gaussian Splatting · Blender (10 views)PSNR: 22.493 -> 23.681Improved
EIG selection instead of random on real-world scenes3D Gaussian Splatting · Mip-NeRF360PSNR: 17.914 -> 20.351Improved
use raw uncertainty (BayesRays) for view selection instead of randomNerfacto · Blender (sequential, 20 views)PSNR: 22.614 -> 22.504Hurt
use ActiveNeRF variance selection instead of randomPlenoxels · Blender (sequential, 20 views)PSNR: 23.906 -> 23.522Hurt
use ActiveNeRF selection instead of random3D Gaussian Splatting · Mip-NeRF360 (sequential)PSNR: 17.914 -> 17.889No clear effect
EIG-based active mapping vs prior active mapping methodsSplaTAM-based active mapping · GibsonCompletion (%): 80.45 -> 92.89Improved
Fisher-based pixel uncertainty vs BayesRays3D Gaussian Splatting · LF datasetAUSE (average): 0.23 -> 0.22No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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