Joint demosaicking and denoising benefits from a two-stage training strategy
From MaRDI portal
Publication:6133115
DOI10.1016/J.CAM.2023.115330zbMath1524.94016arXiv2009.06205OpenAlexW4378648416MaRDI QIDQ6133115
Tieyong Zeng, Gabriele Facciolo, Yu Guo, Qiyu Jin, Jean-Michel Morel
Publication date: 21 July 2023
Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2009.06205
Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Related Items (1)
Cites Work
- IDPCNN: iterative denoising and projecting CNN for MRI reconstruction
- Self-Similarity and Spectral Correlation Adaptive Algorithm for Color Demosaicking
- Joint Demosaicing and Denoising via Learned Nonparametric Random Fields
- Beyond Color Difference: Residual Interpolation for Color Image Demosaicking
- DeepDemosaicking: Adaptive Image Demosaicking via Multiple Deep Fully Convolutional Networks
- Waterloo Exploration Database: New Challenges for Image Quality Assessment Models
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Soft-Edge Assisted Network for Single Image Super-Resolution
- Iterative Joint Image Demosaicking and Denoising Using a Residual Denoising Network
- Self-Similarity Driven Color Demosaicking
- Regularization Approaches to Demosaicking
- Demosaicking by Alternating Projections: Theory and Fast One-Step Implementation
- Multiscale Gradients-Based Color Filter Array Interpolation
This page was built for publication: Joint demosaicking and denoising benefits from a two-stage training strategy
