AI Paper Atlas

Research map / Image generation / Image restoration

NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling

Jaehyun Cho, YOUNGJOON YOO

ECCV 2026 · Image generation › Image restoration · approach: Diffusion priors for denoising and deblurring · 0 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 regional consistency loss (ablation)NGPS · AAPM-MayoPSNR (dB): 36.50 -> 36.68Improved
add inter-slice continuity loss to NGPS (ablation)NGPS · AAPM-MayoPSNR (dB): 36.68 -> 36.58Hurt
add regional consistency and IC losses (ablation)NS-N2N · AAPM-MayoPSNR (dB): 35.43 -> 35.91Improved
use filtered guide for patch matching instead of raw noisy image (ablation)NGPS · LIDC-IDRIPSNR (dB): 28.94 -> 31.03Improved
use bilateral plus median guide instead of NLM guide (ablation)NGPS · LIDC-IDRIguide time (s per triplet): 12.6936 -> 0.1422Improved
retrieve from adjacent slice with guide-based matching instead of same-slice PixelBank (ablation)NGPS · AAPM-MayoPSNR (dB): 35.16 -> 36.68Improved
match on filtered guide instead of adjacent-slice raw-patch bank (ablation)NGPS · LIDC-IDRI 2.5 mmPSNR (dB): 30.18 -> 30.92Improved
increase Top-K ensemble from 1 or 2 to K=4 (ablation)NGPS · LIDC-IDRIPSNR (dB): best at K=4 (PSNR 31.03 dB, SSIM 0.8102)Improved
increase Top-K to 8 or 16 (ablation)NGPS · LIDC-IDRIPSNR (dB): K=4 31.03 dB bestHurt
increase search window from 15 to 23 (ablation)NGPS · LIDC-IDRI 1.25 mmPSNR (dB): 31.08 -> 30.93Hurt
thicker slices (1.25 mm to 2.5 mm)NGPS vs NS-N2N · LIDC-IDRIPSNR drop (dB): -0.16 dB vs -0.63 dBImproved
increase through-plane gap to 5 mmNGPS vs NS-N2N · AAPM-MayoPSNR (dB): 34.48 vs 35.12Hurt

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