AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields

Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua

ICCV 2025 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 0 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-consistent sampling and depth-pushing lossNerfacto · Mip-NeRF360 (9 scenes, 10-110 views averaged)PSNR: 19.05 -> 21.40Improved
add view-consistent sampling and depth-pushing lossNerfacto · Tanks&Temples Intermediate (8 scenes, 10-110 views averaged)PSNR: 18.29 -> 19.45Improved
add view-consistent sampling only (ablation)Nerfacto · Mip-NeRF360 (50 views ablation)PSNR: 18.88 -> 19.34Improved
add depth-pushing loss only (ablation)Nerfacto · Mip-NeRF360 (50 views ablation)PSNR: 18.88 -> 19.10Improved
add depth-pushing loss to view-consistent sampling (ablation)VS-NeRF · Mip-NeRF360 (50 views ablation)PSNR: 19.34 -> 21.57Improved
use distilled features in addition to color features (ablation)VS-NeRF · Mip-NeRF360 (50 views ablation)PSNR: 19.42 -> 21.57Improved
use color features in addition to distilled features (ablation)VS-NeRF · Mip-NeRF360 (50 views ablation)PSNR: 19.96 -> 21.57Improved
reduce distilled feature dimension from 32 to 16 (ablation)VS-NeRF · Mip-NeRF360 (50 views ablation)PSNR: 21.57 -> 20.04Hurt
increase distilled feature dimension from 32 to 64 (ablation)VS-NeRF · Mip-NeRF360 (50 views ablation)PSNR: 21.57 -> 21.65No clear effect
use monocular depth regularization instead of noneNerfacto · Tanks&Temples Intermediate (8 scenes, 10-110 views averaged)PSNR: 18.29 -> 13.81Hurt
add multi-view depth regularizationNerfacto · Mip-NeRF360 (9 scenes, 10-110 views averaged)PSNR: 19.05 -> 20.15Improved
add view-consistent sampling to Mip-NeRF360Mip-NeRF360 · Mip-NeRF360PSNR: 22.54 -> 23.37Improved

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