AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

LOLNerf: Learn From One Look

Daniel Rebain, Mark Matthews, Kwang Moo Yi, Dmitry Lagun, Andrea Tagliasacchi

CVPR 2022 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 84 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 LOLNeRF instead of π-GAN for training-image reconstructionCelebA training-set reconstruction · CelebA training-set reconstruction, 128²PSNR: 23.5 -> 29.1Improved
Use LOLNeRF instead of π-GAN for held-out image reconstructionFFHQ held-out images · FFHQ held-out image reconstruction, 256²PSNR: 21.8 -> 26.2Improved
Use LOLNeRF instead of π-GAN for high-resolution held-out reconstructionFFHQ held-out images · FFHQ held-out image reconstruction, 512²PSNR: 20.9 -> 25.3Improved
Use LOLNeRF instead of π-GAN for novel-view synthesisHUMBI face images · HUMBI novel view synthesisPSNR: 24.5 -> 27.0Improved
Use LOLNeRF rather than supervised depth prediction methods3DFAW · 3DFAW depth predictionDepth Correlation: 50.18 vs 50.81; 50.18 vs 58.68Mixed
Use LOLNeRF instead of π-GAN for unconditional generationCelebA unconditional sampling · CelebA unconditional samplingFID: 14.7 -> 128.2Hurt
Use LOLNeRF instead of π-GAN for unconditional generationCelebA unconditional sampling · CelebA unconditional samplingKID: 0.39 -> 0.11Improved
Use LOLNeRF instead of π-GAN for unconditional generationCelebA unconditional sampling · CelebA unconditional samplingIS: 2.62 -> 2.34Mixed
Increase the training set from very small subsets to more images (ablation)LOLNeRF · Dataset-size ablationNovel-view geometric consistencyImproved
Increase the training set from very small subsets to more images (ablation)LOLNeRF · Dataset-size ablationTraining-image reconstruction accuracyHurt
Add the hard-surface weight prior (ablation)LOLNeRF single-view shape reconstruction · Single-view object reconstructionShape qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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