AI Paper Atlas

Research map / Image generation / Image restoration

Blind2Sound: Self-Supervised Image Denoising without Residual Noise

Jiazheng Liu, Zejin Wang, Bohao Chen, Hua Han

ICCV 2025 · Image generation › Image restoration · approach: Self-supervised image denoising · 2 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
make masked and visible branches independent (IID) (ablation)Blind2Sound · CBSD68 (alpha=0.01, sigma=0.0002)PSNR (dB): 32.19 -> 33.14Improved
make masked and visible branches independent (IID) (ablation)Blind2Sound · CBSD68 (alpha=0.05, sigma=0.02)PSNR (dB): 28.95 -> 29.29Improved
use enhanced noise model M_E instead of M_O (ablation)Blind2Sound · CBSD68 (alpha=0.05, sigma=0.02)PSNR (dB): 29.12 -> 29.29Improved
use enhanced noise model M_E instead of M_S (ablation)Blind2Sound · CBSD68 (alpha=0.05, sigma=0.02)PSNR (dB): 29.14 -> 29.29Improved
joint training of noise estimator and denoiser instead of frozen pre-trained estimator (ablation)Blind2Sound · CBSD68 (alpha=0.01, sigma=0.0002)PSNR (dB): 32.78 -> 33.14Improved
joint training instead of fixed true noise (ablation)Blind2Sound · CBSD68 (alpha=0.01, sigma=0.0002)PSNR (dB): 33.02 -> 33.14Improved
joint training instead of frozen estimator (ablation)Blind2Sound · CBSD68 (alpha=0.05, sigma=0.02)PSNR (dB): 29.24 -> 29.29No clear effect
raise final visible factor from 3 to 11 (ablation)Blind2Sound · CBSD68 (alpha=0.01, sigma=0.02)PSNR (dB): 32.75 -> 32.89Improved
raise final visible factor from 11 to 40 (ablation)Blind2Sound · CBSD68 (alpha=0.01, sigma=0.02)PSNR (dB): 32.89 -> 32.76Hurt
add Cramer Gaussian loss regularization with weight 0.01 (ablation)Blind2Sound · CBSD68PSNR (dB)Improved
add fine-grained sub-block constraint to global Gaussian loss (ablation)Cramer Gaussian loss · BSD68 noise estimation (alpha=0.05, sigma=0.02)estimated (alpha, sigma): 0.039/0.057 -> 0.048/0.022Improved
use Blind2Sound instead of Blind2UnblindBlind2Sound · SIDD RAW BenchmarkPSNR (dB): 50.79 -> 50.92Improved

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