Confidence-based refinement of corrupted depth maps

This paper present a practical depth-map refinement system designed for highly corrupted multiple depth maps. We define a pixel-wise confidence measurement of depth value and apply the three-steps depth-map refinement scheme (i.e.confidence-based depth-map fusion, confidence-weighted bundle optimization and super-pixel-based planar propagation) to maximize the whole reliability of depth maps. Our experimental result shows that our refinement algorithm can dramatically improve highly corrupted depth maps acquired by previous approaches.