AI Paper Atlas

Research map / Image generation / Image restoration

Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres

NeurIPS 2018 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 complex-valued dense layer instead of real-valued (ablation)Single dense layer speckle inversion · 1m fibre, 112x112 speckleMSE: 1025.96 -> 960.31Helped
add l2 weight regularisation to complex layer (ablation)Complex dense layer · 1m fibre, 112x112 speckleMSE: 960.31 -> 962.33No clear effect
add unitary regularisation to complex layer (ablation)Complex dense layer · 1m fibre, 112x112 speckleMSE: 960.31 -> 989.28Hurt
add multiscale pooled output pyramid to complex layer (ablation)Complex dense layer · 1m fibre, 112x112 speckleMSE: 960.31 -> 988.10Hurt
increase speckle image resolution from 14 to 224 pixels (ablation)Single complex layer with l2 regularisation · 28x28 target inversionimage quality (qualitative)Helped
increase fibre length from 1m to 10mComplex dense inversion · Muybridge framesimage quality (qualitative)Hurt

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