Research map / Image generation / Image restoration
Blind Image Denoising via Dependent Dirichlet Process Tree
Fengyuan Zhu, Guangyong Chen, Jianye Hao, Pheng‐Ann Heng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| blind DDPT denoiser vs non-blind BM3D at high noise | DDPT denoiser · TID2008 sigma=100 | PSNR: 23.26 -> 23.32 | Improved |
| blind DDPT denoiser vs BM3D at low noise | DDPT denoiser · TID2008 sigma=10 | PSNR: 35.17 -> 35.11 | Hurt |
| blind DDPT denoiser vs BM3D at low noise | DDPT denoiser · BSDS500 sigma=10 | PSNR: 34.72 -> 34.71 | Hurt |
| blind DDPT denoiser vs BM3D at mid noise | DDPT denoiser · BSDS500 sigma=40 | PSNR: 27.51 -> 27.85 | Improved |
| blind DDPT denoiser vs BM3D SSIM at low noise | DDPT denoiser · TID2008 sigma=10 | SSIM: 0.968 -> 0.958 | Hurt |
| blind DDPT denoiser vs BM3D SSIM at high noise | DDPT denoiser · TID2008 sigma=100 | SSIM: 0.764 -> 0.770 | Improved |
| DDPT vs multiscale noise clinic on Gaussian noise | DDPT denoiser · TID2008 Gaussian sigma=30 | PSNR: 27.02 -> 29.26 | Improved |
| DDPT vs multiscale noise clinic on heterogeneous noise | DDPT denoiser · TID2008 Heterogeneous b=4 | PSNR: 25.54 -> 28.94 | Improved |
| DDPT vs multiscale noise clinic on combined noise | DDPT denoiser · TID2008 Combined noise | PSNR: 25.12 -> 29.87 | Improved |
| DDPT vs multiscale noise clinic on combined noise | DDPT denoiser · BSDS500 Combined noise | SSIM: 0.817 -> 0.904 | Improved |
| DDPT vs multiscale noise clinic on uniform noise | DDPT denoiser · TID2008 Uniform a=30 | PSNR: 31.77 -> 35.27 | Improved |
| DDPT vs multiscale noise clinic on Laplace noise | DDPT denoiser · BSDS500 Laplace 45 | PSNR: 24.29 -> 26.87 | Improved |
Closest papers by meaning
- Variational Denoising Network: Toward Blind Noise Modeling and Removal (NeurIPS 2019 · similarity 0.89)
- On the Posterior Distribution in Denoising: Application to Uncertainty Quantification (ICLR 2024 · similarity 0.86)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.85)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.85)
- Denoising Diffusion Bridge Models (ICLR 2024 · similarity 0.85)
- Listening to the noise: Blind Denoising with Gibbs Diffusion (ICML 2024 · similarity 0.85)
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.
