Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
arXiv:2212.00422 · doi:10.1109/TIP.2024.3436651
Abstract
In the past decade, deep neural networks have revolutionized image denoising in achieving significant accuracy improvements by learning on datasets composed of noisy/clean image pairs. However, this strategy is extremely dependent on training data quality, which is a well-established weakness. To alleviate the requirement to learn image priors externally, single-image (a.k.a., self-supervised or zero-shot) methods perform denoising solely based on the analysis of the input noisy image without external dictionary or training dataset. This work investigates the effectiveness of linear combinations of patches for denoising under this constraint. Although conceptually very simple, we show that linear combinations of patches are enough to achieve state-of-the-art performance. The proposed parametric approach relies on quadratic risk approximation via multiple pilot images to guide the estimation of the combination weights. Experiments on images corrupted artificially with Gaussian noise as well as on real-world noisy images demonstrate that our method is on par with the very best single-image denoisers, outperforming the recent neural network based techniques, while being much faster and fully interpretable.
References in corpus (9)
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
- Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
- Noise2Fast: Fast Self-Supervised Single Image Blind Denoising
- DCT2net: an interpretable shallow CNN for image denoising
- LIDIA: Lightweight Learned Image Denoising with Instance Adaptation
- Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration
- Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach