AI Paper Atlas

Research map / Image generation / Image restoration

Blind Image Denoising via Dependent Dirichlet Process Tree

Fengyuan Zhu, Guangyong Chen, Jianye Hao, Pheng‐Ann Heng

TPAMI 2016 · Image generation › Image restoration · approach: Self-supervised image denoising · 28 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
blind DDPT denoiser vs non-blind BM3D at high noiseDDPT denoiser · TID2008 sigma=100PSNR: 23.26 -> 23.32Improved
blind DDPT denoiser vs BM3D at low noiseDDPT denoiser · TID2008 sigma=10PSNR: 35.17 -> 35.11Hurt
blind DDPT denoiser vs BM3D at low noiseDDPT denoiser · BSDS500 sigma=10PSNR: 34.72 -> 34.71Hurt
blind DDPT denoiser vs BM3D at mid noiseDDPT denoiser · BSDS500 sigma=40PSNR: 27.51 -> 27.85Improved
blind DDPT denoiser vs BM3D SSIM at low noiseDDPT denoiser · TID2008 sigma=10SSIM: 0.968 -> 0.958Hurt
blind DDPT denoiser vs BM3D SSIM at high noiseDDPT denoiser · TID2008 sigma=100SSIM: 0.764 -> 0.770Improved
DDPT vs multiscale noise clinic on Gaussian noiseDDPT denoiser · TID2008 Gaussian sigma=30PSNR: 27.02 -> 29.26Improved
DDPT vs multiscale noise clinic on heterogeneous noiseDDPT denoiser · TID2008 Heterogeneous b=4PSNR: 25.54 -> 28.94Improved
DDPT vs multiscale noise clinic on combined noiseDDPT denoiser · TID2008 Combined noisePSNR: 25.12 -> 29.87Improved
DDPT vs multiscale noise clinic on combined noiseDDPT denoiser · BSDS500 Combined noiseSSIM: 0.817 -> 0.904Improved
DDPT vs multiscale noise clinic on uniform noiseDDPT denoiser · TID2008 Uniform a=30PSNR: 31.77 -> 35.27Improved
DDPT vs multiscale noise clinic on Laplace noiseDDPT denoiser · BSDS500 Laplace 45PSNR: 24.29 -> 26.87Improved

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