Research map / Image generation / Image restoration
Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Remove all additive constants, including batch-normalization offsets (ablation) | DnCNN · Noise levels outside the training range | PSNR | Helped |
| Remove all additive constants (ablation) | DnCNN, Recurrent CNN, UNet, and Simplified DenseNet · Noise levels outside the training range | PSNR | Helped |
| Remove all additive constants (ablation) | DnCNN, Recurrent CNN, UNet, and Simplified DenseNet · Noise levels outside the training range | SSIM | Helped |
| Remove all additive constants (ablation) | CNN architectures trained on Gaussian noise · Uniform test noise | PSNR | Helped |
| Remove all additive constants (ablation) | CNN for image restoration · Noise levels outside training range at fixed blur | PSNR | Helped |
| Remove all additive constants (ablation) | CNN for image restoration · Unseen blur levels | PSNR | No clear effect |
Closest papers by meaning
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.93)
- Toward Convolutional Blind Denoising of Real Photographs (CVPR 2019 · similarity 0.92)
- Variational Denoising Network: Toward Blind Noise Modeling and Removal (NeurIPS 2019 · similarity 0.92)
- Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators (ICLR 2020 · similarity 0.92)
- High-Quality Self-Supervised Deep Image Denoising (NeurIPS 2019 · similarity 0.91)
- Generalization in diffusion models arises from geometry-adaptive harmonic representations (ICLR 2024 · 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.