Estimation of signal-dependent noise level function using multi-column convolutional neural network
Jingyu Yang, Xin Liu, Xiaolin Song, Kun Li · 2017
To estimate the levels of signal-dependent noise (SDN) from a single image is challenging. This paper proposes a novel method to estimate the noise level function (NLF) from a single image using a Multi-column Convolutional Neural Network (MC-Net) with an end-to-end architecture. The MC-Net is trained on a synthesized dataset containing noisy images with known NLFs, and it allows to learn rich hierarchical features using three sub-networks. Moreover, this method performs end-to-end training to retain more details for pixel-wise noise level estimation. Experimental results indicate that our method is accurate and robust to estimate NLFs of SDN for various types of images.