Dynamic Range Hallucination using Deep Convolution Networks

Dynamic Range Hallucination using Deep Convolutional Networks • In this project, our aim is to predict an HDR image in a device that has dynamic range different to that of capturing device, from a corresponding overexposed and/or underexposed LDR image(camera image)

•Our solution is based on the assumption that there exists a mapping from the low dynamic range image(camera image) to our HDR display, which can be predicted through learning based approach using Convolutional Neural Networks(CNNs) either by pure rote learning or clue based learning.