# Fully Convolutional Pixel Adaptive Image Denoiser

arXiv: https://arxiv.org/abs/1807.07569 · HTML: https://mlsanity.com/paper/1807.07569/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 8 of 8)

- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising](https://mlsanity.com/paper/2303.14934/) (2023)
- [FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise](https://mlsanity.com/paper/2105.10967/) (2021)
- [Real-World Denoising via Diffusion Model](https://mlsanity.com/paper/2305.04457/) (2023)
- [Blind2Sound: Self-Supervised Image Denoising without Residual Noise](https://mlsanity.com/paper/2303.05183/) (2023)
- [NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations](https://mlsanity.com/paper/2106.11644/) (2021)
- [Zero-Shot Image Denoising for High-Resolution Electron Microscopy](https://mlsanity.com/paper/2406.14264/) (2024)

## Abstract (arXiv)

We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully convolutional neural network as well as adaptively fine-tune the supervised model for each given noisy image. We significantly extend the framework of the recently proposed Neural AIDE, which formulates the denoiser to be context-based pixelwise mappings and utilizes the unbiased estimator of MSE for such denoisers. The two main contributions we make are; 1) implementing a novel fully convolutional architecture that boosts the base supervised model, and 2) introducing regularization methods for the adaptive fine-tuning such that a stronger and more robust adaptivity can be attained. As a result, FC-AIDE is shown to possess many desirable features; it outperforms the recent CNN-based state-of-the-art denoisers on all of the benchmark datasets we tested, and gets particularly strong for various challenging scenarios, e.g., with mismatched image/noise characteristics or with scarce supervised training data. The source code of our algorithm is available at https://github.com/csm9493/FC-AIDE-Keras.