AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields

Muyu Xu, Fangneng Zhan, Jiahui Zhang, Yingchen Yu, Xiaoqin Zhang, Christian Theobalt, Ling Shao, Shijian Lu

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 25 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 Wavelet MVS (WMVS) (ablation)GeoNeRF baseline · DTUPSNR: 27.67 -> 27.97Improved
add Wavelet MVS (WMVS) (ablation)GeoNeRF baseline · NeRF SyntheticPSNR: 24.80 -> 24.63Hurt
add Wavelet MVS (WMVS) (ablation)GeoNeRF baseline · LLFFPSNR: 23.22 -> 23.23No clear effect
add Frequency-guided Sampling Strategy (FSS) (ablation)WMVS model · DTUPSNR: 27.97 -> 28.90Improved
add Frequency-guided Sampling Strategy (FSS) (ablation)WMVS model · NeRF SyntheticLPIPS: 0.183 -> 0.119Improved
add Hybrid Neural Renderer (HNR) (ablation)WMVS + FSS model · DTUPSNR: 28.90 -> 29.16Improved
add Hybrid Neural Renderer (HNR) (ablation)WMVS + FSS model · LLFFLPIPS: 0.227 -> 0.206Improved
add Weighted Frequency Loss (WFL) (ablation)WMVS + FSS + HNR model · DTUPSNR: 29.16 -> 29.55Improved
add WFL (ablation)WMVS + FSS + HNR model · LLFFLPIPS: 0.206 -> 0.212Hurt
train from scratch end-to-end vs pretrained CasMVSNet checkpointGeoNeRF · DTUPSNR: 29.02 -> 27.67Hurt
compare WaveNeRF with pretrained-MVS GeoNeRF*WaveNeRF · LLFFPSNR: 24.28 vs 24.31No clear effect
use wavelet-domain features and FSS for renderingWaveNeRF · DTUHFIV: 0.103 -> 0.0521Improved

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