AI Paper Atlas

Research map / Image generation / Image restoration

Robust Test-Time Adaptation for Single Image Denoising Using Deep Gaussian Prior

Qing Ma, Pengwei Liang, Xiong Zhou, Jiayi Ma, Junjun Jiang, Zhe Peng

ICCV 2025 · Image generation › Image restoration · approach: Self-supervised image denoising · 3 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
initialize ZS-N2N from a pre-trained Gaussian denoiser (10 iterations vs 2000) (ablation)ZS-N2N · Kodak24 Gaussian sigma=50PSNR (dB): 24.81 -> 26.07; time 9.04 s -> 0.07 sImproved
fine-tune pre-trained Gaussian denoiser with ZS-N2N pair construction (ablation)Pre-trained Neighbor2Neighbor denoiser · Kodak24 Gaussian sigma=25 (in-distribution)PSNR (dB): 29.70 -> 29.33Hurt
fine-tune pre-trained denoiser with test-time adaptation on out-of-distribution noisePre-trained Neighbor2Neighbor denoiser · Kodak24 Gaussian sigma=50PSNR (dB): 20.94 -> 27.11Improved
fine-tune pre-trained denoiser with test-time adaptation on Poisson noisePre-trained Neighbor2Neighbor denoiser · Kodak24 Poisson lambda=10PSNR (dB): 19.94 -> 26.64Improved
add test-time adaptation on in-distribution Gaussian noisePre-trained Neighbor2Neighbor denoiser · Kodak24 Gaussian sigma=25PSNR (dB): 29.70 -> 30.75 (+1.05 dB)Improved
add Gaussian pre-training before adaptation with pixel-bank pairs (ablation)Ours · Kodak24 Gaussian sigma=25PSNR (dB): 29.65 -> 30.75Improved
construct pairs by non-local pixel search (pixel bank) instead of downsampling (ablation)test-time fine-tuning · Kodak24 fine-tuning over iterationsPSNR (dB): peak 27.14 vs NB2NB 26.36 and ZS-N2N 26.40Improved
run more fine-tuning iterations with ZS-N2N pair construction (ablation)ZS-N2N pairs · Kodak24 fine-tuning over iterationsPSNR (dB): 26.40 -> 16.42 over iterationsHurt
apply Ours to real-world PolyU noise without pre-training (vs with pre-trained model) (ablation)Ours · PolyU real-worldPSNR (dB): 36.12 (without pre-train) vs 36.10 (pre-trained only)No clear effect

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