AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NAN: Noise-Aware NeRFs for Burst-Denoising

Naama Pearl, Tali Treibitz, Simon Korman

CVPR 2022 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 43 citations (OpenAlex)

Check 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
Use L1 loss instead of L2 lossNAN · LLFF-NPSNR: 0.4 dBImproved
Add a 3×3 Pre-Net convolution before feature extraction (ablation)NAN · LLFF-N, gain 16denoising performanceImproved
Add a five-head self-attention transformer for cross-view feature aggregation (ablation)NAN · LLFF-N, gain 16denoising performanceImproved
Add per-pixel, per-channel noise variances as features (ablation)NAN · LLFF-N, gain 16denoising performanceImproved
Replace per-view scalar color blending weights with per-view spatial, per-channel 3D blending kernels (ablation)NAN · LLFF-N, gain 16denoising performanceImproved
Add spatial awareness through 3D-blending kernels (ablation)NAN · LLFF-N, gain 16depth errorImproved
Use bilateral filtering as inference-time post-processingNAN · LLFF-Nnoise in homogeneous regionsImproved

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