Noise Reduction of Depth CameraImages using Deep Neural Networks

Today, infrared sensors or depthsensors are widely used to control applications, games, information acquisition, dynamic and static 3D scenes. Despite the widespread use of these images, their quality is limited to low-quality images, as the infrared sensor doesnothavehigh resolutionand the images produced by it have noise. Therefore, given the problems and the importance of using 3-D images, the quality of these images should be improved in order to provide accurate images from depthcameras. In this paper,thenoise reduction ofdepthimages using convolutional neural networks is considered. A convolutional neural network with a depth of 20 and three layers and a pre-trained neural network is used. We developed the system and tested its performance for two datasets of depthand color images, Middlebury and EURECOM Kinect Face. Results showthatforEURECOM Kinect Face images, PSNR improvement isapproximately8 to 15 dB and for Middlebury images the PSNR improvementis about 5 to 14 dB.