AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Neural Fourier Filter Bank

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: NeRF for scene decomposition and understanding · 27 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
remove Fourier encoding from grid features (ablation)NFFB · TokyoPSNR: 30.48 vs 31.57Helped
replace sine activations with ReLU (ablation)NFFB · TokyoPSNR: 30.39 vs 31.57Helped
use only grid features, without Fourier encoding and MLP composition (ablation)NFFB · TokyoPSNRHurt
use only the MLP composition, without grid features (ablation)NFFB · TokyoPSNRHurt
reduce the Fourier grid feature to a single level (ablation)NFFB · TokyoPSNRHurt
increase MLP size (ablation)NFFB · TokyoPSNRHelped
increase base grid resolution (ablation)NFFB · TokyoPSNRHelped
increase grid-resolution scaling coefficient (ablation)NFFB · TokyoPSNRHelped
tune Fourier-feature variance to a suitable range (ablation)NFFB · NeRF synthetic BlenderPSNRMixed
tune the sine-layer scaling factor (ablation)NFFB · NeRF synthetic BlenderPSNRMixed

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