AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

DeepPhaseCut: Deep Relaxation in Phase for Unsupervised Fourier Phase Retrieval

Eunju Cha, Chanseok Lee, Mooseok Jang, Jong Chul Ye

TPAMI 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval · 22 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 cycle consistency loss (ablation)DeepPhaseCut · Microscopy beads (1,000 test images)PSNR (dB): 9.719 -> 24.284Improved
add cycle consistency loss (ablation)DeepPhaseCut · Microscopy beads (1,000 test images)SSIM: 0.098 -> 0.748Improved
add PhaseCut loss (ablation)DeepPhaseCut · Microscopy beads (1,000 test images)PSNR (dB): 21.513 -> 24.284Improved
add PhaseCut loss (ablation)DeepPhaseCut · Microscopy beads (1,000 test images)SSIM: 0.676 -> 0.748Improved
add adversarial loss (ablation)DeepPhaseCut · Microscopy beads (1,000 test images)PSNR (dB): 23.653 -> 24.284Improved
add adversarial loss (ablation)DeepPhaseCut · Microscopy beads (1,000 test images)SSIM: 0.741 -> 0.748Improved
use both phase network and image refinement network instead of a single generator (ablation)DeepPhaseCut · fastMRIPSNR (dB): 3.01 ~ 13.28 dB better than the ablated networksImproved
replace HIO and PhaseCut with feed-forward DeepPhaseCutPhaseCut · CelebA (2,478 test images)runtime (sec): 1044.720 -> 0.048Improved
use DeepPhaseCut instead of the baselinesbaselines · CelebA (2,478 test images)PSNR (dB): 1.06 ~ 7.55 dBImproved
use DeepPhaseCut instead of HIO and PhaseCut on complex-valued dataHIO · fastMRI (4,873 test images)PSNR (dB): 18.806 -> 19.820Improved
use DeepPhaseCut instead of prDeep (pretrained denoiser regularizer)prDeep · Microscopy beads (1,000 test images)PSNR (dB): 23.849 -> 24.284Improved
initialize On-RED with HIO resultHIO · CelebA (2,478 test images)PSNR (dB): 19.573 -> 19.796No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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