Image Denoising is the task of removing noise from an image, e.g. the application of Gaussian noise to an image.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Clean video frames for dynamic scenes cannot be captured with a long-exposure shutter or averaging multi-shots as was done for static images.
Lacking rich and realistic data, learned single image denoising algorithms generalize poorly to real raw images that do not resemble the data used for training.
The effectiveness of the proposed methods are experimentally shown over two datasets: 1) classic test images corrupted with Gaussian noise, and 2) fluorescence microscopy images corrupted with real Poisson-Gaussian noise.
This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline.
Convolutional neural network (CNN)-based image denoising methods typically estimate the noise component contained in a noisy input image and restore a clean image by subtracting the estimated noise from the input.
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing.
In this paper, we propose an alternating directional 3D quasi-recurrent neural network for hyperspectral image (HSI) denoising, which can effectively embed the domain knowledge -- structural spatio-spectral correlation and global correlation along spectrum.
The average residual noise in the resulting images is below that of the standard double-shot technique.