Fully Convolutional Pixel Adaptive Image Denoiser
This work addresses image denoising for computer vision applications, offering a robust solution that is incremental by extending the Neural AIDE framework with architectural and regularization improvements.
The paper tackles image denoising by proposing FC-AIDE, a method that combines a fully convolutional neural network with adaptive fine-tuning for each noisy image, resulting in outperforming recent CNN-based state-of-the-art denoisers on all tested benchmark datasets, particularly in challenging scenarios like mismatched image/noise characteristics or scarce training data.
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.