Research map / Image generation / Image restoration
Integrating Reweighted Least Squares with Plug-and-Play Diffusion Priors for Noisy Image Restoration
Ji Li, Chao Wang
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 |
|---|---|---|---|
| use l_q fidelity with q=0.5 (IRLS) instead of Gaussian l2 fidelity (q=2 DPS) | PnP diffusion prior · FFHQ denoising, impulse noise 0.5 | PSNR: 16.71 -> 28.36 | Improved |
| replace DRUnet/TV regularizer with diffusion/flow prior | IRLS PnP · AFHQ-Cat inpainting | PSNR: 16.12 -> 26.16 (vs DRUnet) | Improved |
| lower q from 1.0 to 0.5 in l_q fidelity (ablation) | IRLS-PnPDP · AFHQ-Cat denoising | PSNR: 27.76 -> 29.73 | Improved |
| lower q below 0.5 (0.2-0.4) (ablation) | IRLS-PnPDP · AFHQ-Cat denoising | PSNR: 29.73 -> 29.62 (q=0.2) | No clear effect |
| IRLS reweighting with l_q loss in DPS guidance rather than raw l_q gradient (ablation) | DPS · FFHQ impulse noise | visual quality | Improved |
| ImageNet: ours vs DRUnet on 4x SR | IRLS-PnPDP · ImageNet 4x super-resolution | PSNR: 10.45 -> 16.36 | Improved |
| ImageNet: ours vs DRUnet on denoising SSIM | IRLS-PnPDP · ImageNet denoising | SSIM: 0.675 -> 0.679 | No clear effect |
Closest papers by meaning
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.91)
- Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems (NeurIPS 2024 · similarity 0.90)
- Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise (NeurIPS 2024 · similarity 0.90)
- Improving Diffusion-Based Image Restoration with Error Contraction and Error Correction (AAAI 2024 · similarity 0.89)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.89)
- Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual (CVPR 2025 · similarity 0.89)
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.
