AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis

Huan Wang, Jian Ren, Zeng Huang, Kyle Olszewski, Menglei Chai, Yun Fu, Sergey Tulyakov

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 73 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
train the NeRF network on 10k pseudo images instead of 0.1k original images (ablation)NeRF network as light field · Legotest PSNR: 19.81 -> 26.67Improved
use the deep residual R2L network instead of the 11-layer NeRF network at 10k pseudo images (ablation)R2L W181D88 · Legotest PSNR: 26.67 -> 29.50Improved
add original real images to pseudo data (ablation)R2L W181D88 · Legotest PSNR: 29.50 -> 30.09Improved
add original real images to pseudo data (ablation)R2L W256D88 · NeRF syntheticPSNR: 30.48 -> 31.87Improved
add original real images to pseudo data (ablation)R2L W256D88 · DONeRF syntheticPSNR: 32.67 -> 35.45Improved
add original real images to pseudo data (ablation)R2L W256D88 · NeRF real-worldPSNR: 27.58 -> 27.79Improved
add original real images to pseudo dataR2L W256D88 · NeRF real-worldLPIPS: 0.0733 -> 0.0968Hurt
add dropout to NeRF network on original data (ablation)NeRF network · Legotest PSNR: 19.81 -> 19.83No clear effect
add batch norm to NeRF network on original data (ablation)NeRF network · Legotest PSNR: 19.81 -> 19.76No clear effect
add residual connections to the deep MLP (ablation)R2L · Legotest PSNRImproved
increase pseudo sample size beyond 5k images (ablation)R2L W181D88 · Legotest PSNRNo clear effect
add hard example mining (r > 0) to training batches (ablation)R2L W181D88 · Legotrain and test PSNRImproved

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