Microsoft has released the Kinect for Windows v2 sensor (Kinect v2) recently as an improved version of its original Kinect (Kinect v1). The depth and color resolutions of the Kinect v2 have been approximately doubled compared to the Kinect v1. Also, the depth sensing mechanism has been changed from the structured lighting IR sensing to the time of flight (ToF) technology. Accordingly, depth artifacts of the Kinect v1 such as random holes have been alleviated significantly, but the holes still exist around object boundaries in the Kinect v2.
In this paper, we exploit the edge information from the color image to fill the holes in the depth image of the Kinect v2.
*ITRC 기여율 = 1