Learning Adaptive Parameter Tuning for Image Processing

TL;DR

This paper introduces a flexible learning-based approach for adaptive image processing that tunes parameters locally based on image features, improving performance in denoising, demosaicing, and deblurring tasks.

Contribution

It presents a novel method to learn local parameter tuning strategies from image features using a user-defined cost function, applicable to multiple classical image processing problems.

Findings

Improved image quality in denoising, demosaicing, and deblurring.

Learned strategies align with existing theoretical results.

Flexible framework adaptable to different image quality metrics.

Abstract

The non-stationary nature of image characteristics calls for adaptive processing, based on the local image content. We propose a simple and flexible method to learn local tuning of parameters in adaptive image processing: we extract simple local features from an image and learn the relation between these features and the optimal filtering parameters. Learning is performed by optimizing a user defined cost function (any image quality metric) on a training set. We apply our method to three classical problems (denoising, demosaicing and deblurring) and we show the effectiveness of the learned parameter modulation strategies. We also show that these strategies are consistent with theoretical results from the literature.