Project DetailsWithin the field of Image Quality Assessment (IQA), there are a few main methods of producing an evaluation. One such method, which this project focuses on, is a Perceptual index meaning a measure of a photos visual quality, what looks good to human eyes.
Our goal is to create such a measure, which can assist Deep Neural Networks to perform various tasks upon depth images. Examples for tasks can be classification, denoising, compression and reconstruction, etc. Our work includes an attempt to create such a measure, using the responses of a DNN we design for different datasets.
We base our work on existing IQA measures for RGB photos, and we make adjustments based on an understanding of the behavior of depth maps. Another product of our work is a module which calculates the measure based on the response of our DNN to the data. Lastly, we test the measure on a series of different datasets and show that the measure improves the performance of an existing DNN.
