AI Paper Atlas

Research map / Image generation / Super-resolution

SIGNET: Efficient Neural Representation for Light Fields

Brandon Yushan Feng, Amitabh Varshney

ICCV 2021 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 42 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 Gegenbauer input transformation on top of sine-activation MLP (SIREN vs SIGNET) (ablation)SIREN · Stanford static light fieldsreconstruction qualityImproved
add Gegenbauer input transformation to a ReLU MLP (CoordinateReLU vs GegenbauerReLU) (ablation)CoordinateReLU · Stanford static light fieldsreconstruction qualityImproved
replace Fourier input transformations with Gegenbauer (GegenbauerReLU vs FourierReLU, DiscreteFourierReLU, DiscreteFourierSine) (ablation)MLP light field representation · Stanford static light fields (3 scenes average)reconstruction qualityImproved
use Gegenbauer transformation instead of Fourier-style ones (ablation)SIGNET · Stanford static light fieldstraining convergenceImproved
increase number of Gegenbauer basis functions C (beta 0.25, 0.5, 2, 4) (ablation)SIGNET · LegoPSNR: gain diminishes after C > 1024No clear effect
increase number of layers L (ablation)SIGNET · LegoPSNR: saturates at 10 layersImproved
increase hidden width M (ablation)SIGNET · LegoPSNRNo clear effect
increase Gegenbauer alpha above default 0.5 (ablation)SIGNET · LegoPSNR: alpha larger than 0.5 declinesHurt
add quantization and weight pruning to SIGNET weightsSIGNET · light field compressionbitrate and PSNR: 15-fold bitrate reduction, PSNR decreased by less than 0.1Improved
use SIGNET instead of AMDE dictionary compressionAMDE · Legostorage size: 29.3 -> 9.0Improved

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