Abstract
We describe a me thod to produce detailed high resolu-tion depth mcps from aggressively subsampled depth mea-surements.Our method fully uses the relationshp between image segmentalion boundaries and depth boundaries.It uses an image combined with a low resolution depth map.1)The image is segmented with the guidance of sparse depth sanples.2)Each segment has its depth field re-constructed independently using a novel smoothing method.3)For videos,time-stamped sanples from near frames are incorporated.The paper shows reconstruction results of super resolution from x4 to x100,while previous methods mainly work on x2 to x16.The method is tested on four diferent datasets and six video sequences,covering quite di ferent regimes,and it outperforms recent state of the art methods quantitatively and qualitative ky.We also demon- strate that depth maps produced by our method can be used by applications such as hand trackers,while depth maps from other methods have problems.