AI Paper Atlas

Research map / Optimization / Optimizers

It Has Potential: Gradient-Driven Denoisers for Convergent Solutions to Inverse Problems

Regev Cohen, Yochai Blau, Daniel Freedman, Ehud Rivlin

NeurIPS 2021 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 11 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
gradient-of-potential denoiser (GraDnCNN) with backtracking GD instead of DnCNN in RED-SDRED-SD · Gaussian deblurring Set11PSNR (dB): 28.69 -> 29.42Improved
GraDnCNN Algorithm 1 instead of PnP-PGD DnCNNPnP-PGD · Super resolution Set11PSNR (dB): 26.20 -> 26.69Improved
constrain potential to be convex (DnICNN) instead of unconstrained GraDnCNN (ablation)Algorithm 1 · Gaussian deblurring Set11PSNR (dB): 29.42 -> 28.91Hurt
difference-of-ICNNs potential instead of GraDnCNN (ablation)Algorithm 1 · Gaussian deblurring BSD500PSNR (dB): 28.91 -> 28.41Hurt
convex potential (DnICNN) for convergence speed (ablation)Algorithm 1 · Convergence on Set11/BSD500convergence rateImproved
backtracking step size with explicit potential vs PnP-PGD fixed stepPnP-PGD · Convergence, 400 iterationsconvergenceImproved

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