AI Paper Atlas

Research map / 3D vision / Face and shape

Fast Training of Neural Lumigraph Representations using Meta Learning

Alexander William Bergman, Petr Kellnhofer, Gordon Wetzstein

NeurIPS 2021 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 4 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
Apply MetaNLR++ instead of NLR++NLR++ · DTUtime to 25dB PSNR: 3.2 min. -> 1.9 min.Improved
Apply MetaNLR++ instead of NLR++NLR++ · DTUtime to 30dB PSNR: 37.4 min. -> 22.5 min.Improved
Apply MetaNLR++ instead of NLR++NLR++ · DTUMaximum PSNR: 31.02dB -> 30.57dBHurt
Apply MetaNLR++ instead of NLR++NLR++ · NLR datasetPSNR after 30 minutes: 28.22 -> 31.12Improved
Apply MetaNLR++ instead of NLR++NLR++ · NLR datasetLPIPS after 30 minutes: 0.145 -> 0.083Improved
Apply MetaNLR++ instead of NLR++NLR++ · NLR datasetConvergence PSNR: 35.54 -> 37.55Improved
Apply MetaNLR++ instead of NLR++NLR++ · NLR datasetConvergence LPIPS: 0.046 -> 0.034Improved
Add meta initialization to all networks rather than no meta initialization (ablation)CNN E/D with learned Γ · DTU, after 10 minutesPSNR: 27.32dB -> 29.91dBImproved
Add meta initialization to Φ only rather than no meta initialization (ablation)CNN E/D with learned Γ · DTU, after 10 minutesPSNR: 27.32dB -> 28.48dBImproved
Add meta initialization to all networks rather than no meta initialization (ablation)CNN E/D with fixed Γ · DTU, after 10 minutesPSNR: 28.62dB -> 29.88dBImproved
Add learned Γ instead of fixed Γ (ablation)RGB pixel features without meta initialization · DTU, after 10 minutesPSNR: 27.85dB -> 26.82dBHurt
Add learned Γ instead of fixed Γ (ablation)CNN E/D without meta initialization · DTU, after 10 minutesPSNR: 28.62dB -> 27.32dBHurt

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