Research map / Image generation / Image restoration
Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks
Filippos Kokkinos, Stamatios Lefkimmiatis
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 |
|---|---|---|---|
| train on 40,000-image MIT subset instead of 200 MSR images | ResDNet demosaicking network · MSR noise-free (linRGB) | PSNR: 41.0 -> 42.6 | Improved |
| train on 40,000-image MIT subset instead of MSR | ResDNet demosaicking network · Kodak demosaick-only | PSNR: 39.2 -> 41.5 | Improved |
| train on 200 noisy MSR images instead of Gaussian-perturbed MIT data (Gharbi) | Joint demosaick-denoise · MSR noisy (linRGB) | PSNR: 38.6 -> 39.2 | Improved |
| train on 200 noisy MSR images instead of Gaussian-perturbed MIT data (Gharbi) | Joint demosaick-denoise · MSR noisy (sRGB) | PSNR: 32.6 -> 33.3 | Improved |
| use weight-shared unrolled MM network with fewer parameters instead of Gharbi network | ResDNet demosaicking network · Model size | trainable parameters: 559,776 -> 380,356 | Improved |
| apply network to Fuji X-Trans CFA instead of Bayer, trained on MSR | ResDNet demosaicking network · Fuji X-Trans noise-free (linear) | PSNR: 39.7 -> 39.9 | Improved |
| train on MSR (200 images) vs MIT subset | ResDNet demosaicking network · Moire demosaick-only | PSNR: 29.7 -> 37.0 | Improved |
Closest papers by meaning
- End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution (CVPR 2021 · similarity 0.92)
- Joint Demosaicking and Denoising by Fine-Tuning of Bursts of Raw Images (ICCV 2019 · similarity 0.92)
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.92)
- Unsupervised Image Restoration Using Partially Linear Denoisers (TPAMI 2021 · similarity 0.91)
- Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty (AAAI 2021 · similarity 0.90)
- Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems (ICCV 2017 · similarity 0.90)
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.
