AI Paper Atlas

Research map / Image generation / Image restoration

Bessel Equivariant Networks for Inversion of Transmission Effects in Multi-Mode Optical Fibres

Joshua Mitton, Simon Peter Mekhail, Miles Padgett, Daniele Faccio, Marco Aversa, Roderick Murray-Smith

NeurIPS 2022 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 5 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 post-processing to the Bessel equivariant model (ablation)Bessel Equivariant · Theoretical TM fMNISTtest loss: 0.0139 -> 0.0032Improved
Add post-processing to the Bessel equivariant model (ablation)Bessel Equivariant · ImageNet 256×256test loss: 0.0574 -> 0.0159Improved
Add post-processing to the Bessel equivariant model (ablation)Bessel Equivariant · Real MMF MNISTtest loss: 0.03125 -> 0.01453Improved
Add post-processing to the Bessel equivariant model (ablation)Bessel Equivariant · Real MMF fMNISTtest loss: 0.03140 -> 0.01749Improved
Use Bessel equivariant inversion instead of the complex linear modelTheoretical TM model trained on fMNIST · MNIST test (trained on fMNIST)test loss: 0.0363 -> 0.0026Improved
Add post-processing to the Bessel model on an out-of-domain dataset (ablation)Bessel Equivariant trained on fMNIST · MNIST test (trained on fMNIST)test loss: 0.0026 -> 0.0028No clear effect
Relax the diagonal mapping to allow ten off-diagonal offsets (ablation)Bessel Equivariant with post-processing · Real MMF MNISTtest loss: 0.01453 -> 0.00576Improved
Relax the diagonal mapping to allow ten off-diagonal offsets (ablation)Bessel Equivariant with post-processing · Real MMF fMNISTtest loss: 0.01749 -> 0.01162Improved
Use a full rather than diagonal mapping between Bessel bases (ablation)Bessel Equivariant with post-processing · Real MMF MNISTtest loss: 0.01453 -> 0.00378Improved
Use a full rather than diagonal mapping between Bessel bases (ablation)Bessel Equivariant with post-processing · Real MMF fMNISTtest loss: 0.01749 -> 0.00964Improved
Increase Gaussian noise in the speckled input (ablation)Bessel Equivariant + Post Proc · Theoretical TM fMNIST, noise level 0.01 to 0.5test loss: 0.0033 -> 0.0049Hurt
Increase Gaussian noise in the speckled input (ablation)Bessel Equivariant · Theoretical TM fMNIST, noise level 0.01 to 0.5test loss: 0.0142 -> 0.0377Hurt

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