Denoising is one of the fundamental steps of the processing pipeline that converts data captured by a camera sensor into a display-ready image or video. It is generally performed early in the pipeline, usually before demosaicking, although studies swapping their order or even conducting them jointly have been proposed. With the advent of deep learning, the quality of denoising algorithms has steadily increased. Even so, modern neural networks still have a hard time adapting to new noise levels and scenes, which is indispensable for real-world applications. With those in mind, we propose a self-similarity-based denoising scheme that weights both a pre- and a post-demosaicking denoiser for Bayer-patterned CFA video data. We show that a balance between the two leads to better image quality, and we empirically find that higher noise levels benefit from a higher influence pre-demosaicking. We also integrate temporal trajectory prefiltering steps before each denoiser, which further improve texture reconstruction. The proposed method only requires an estimation of the noise model at the sensor, accurately adapts to any noise level, and is competitive with the state of the art, making it suitable for real-world videography.

Identifying and mapping fractures and faults are important in geosciences, especially in earthquake hazard and geological reservoir studies. This mapping can be done manually in optical images of the earth surface, yet it is time consuming and it requires an expertise that may not be available. Building upon a recent prior study, we develop a deep learning approach, based on a variant of a U-Net neural network, and apply it to automate fracture and fault mapping in optical images and topographic data. We show that training the model with a realistic knowledge of fracture and fault uneven distributions and trends, and using a loss function that operates at both pixel and larger scales through the combined use of weighted Binary Cross Entropy and Intersection over Union, greatly improves the predictions, both qualitatively and quantitatively. As we apply the model to a site differing from those used for training, we demonstrate its enhanced generalization capacity.

Synthetic Aperture Radar (SAR) image despeckling is still an open issue. Several approaches have been proposed in the last decades. The recently proposed Non Local approaches are often considered as the state of art of SAR despeckling. The difference between the NL algorithms presented in literature is mainly related to the adopted distance metric between patches and on the rule used for averaging the selected pixels. Within this manuscript a new metric for selecting similar patches is presented. The metric is based on the statistical distribution of the complex noisy image. The Kolmogorov-Smirnov (KS) test is adopted to compare the statistical distribution and to select similar patches. The approach has been tested and validate on real data, showing interesting performances.