Depth super resolution using bilateral filter

Depth maps are used in many applications, e.g. 3D television, stereo matching, segmentation, etc. Recently, a new generation of active 3D range sensors, such as time-of-flight (TOF) cameras, enables recording of full frame depth maps at video frame rate. Unfortunately, depth maps captured with the TOF cameras have limited resolution and poor image quality, being serverely influenced by the random and systematic noise, which makes them innaposite for generating high quality 3D images. In this paper, we proposed a method to enhance the quality and increase the spatial resolution of range data by upsampling the range information with the data from a high resolution video camera. Our algorithm is an adaptive upsampling filter that takes into account the inherent noisy nature of depth data. Thus, we can improve reconstruction quality, boost the resolution of the data to that of the video sensor, and prevent unwanted artifacts like texture copy into geometry.