AI Paper Atlas

Research map / Image generation / GANs

Adversarial Regularizers in Inverse Problems

Sebastian Lunz, Ozan Öktem, Carola-Bibiane Schönlieb

NeurIPS 2018 · Image generation › GANs · approach: Generative adversarial network theory · 77 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
Replace Total Variation with an unsupervised adversarial regularizerDenoising · BSDS denoisingPSNR (dB): 26.3 -> 28.2Improved
Use an unsupervised adversarial regularizer instead of supervised Denoising N.N.Denoising · BSDS denoisingPSNR (dB): 28.8 -> 28.2Hurt
Replace Total Variation with an unsupervised adversarial regularizerCT reconstruction · LIDC CT high noisePSNR (dB): 27.7 -> 30.5Improved
Replace Total Variation with an unsupervised adversarial regularizerCT reconstruction · LIDC CT low noisePSNR (dB): 30.0 -> 32.5Improved
Use an adversarial regularizer instead of REDCT reconstruction · LIDC CT high noisePSNR (dB): 29.9 -> 30.5Improved
Use an adversarial regularizer instead of REDCT reconstruction · LIDC CT low noisePSNR (dB): 32.8 -> 32.5Hurt
Use an adversarial regularizer instead of supervised Post-ProcessingCT reconstruction · LIDC CT high noisePSNR (dB): 31.2 -> 30.5Hurt
Use an adversarial regularizer instead of supervised Post-ProcessingCT reconstruction · LIDC CT low noisePSNR (dB): 33.6 -> 32.5Hurt
Add partially reconstructed images to the regularizer training samplesAdversarial Regularizer · CT reconstructionperformanceImproved

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