Title :
Confidence-based refinement of corrupted depth maps
Author :
Ikehata, Satoshi ; Aizawa, K.
Author_Institution :
Univ. of Tokyo, Tokyo, Japan
Abstract :
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.
Keywords :
image enhancement; image restoration; confidence-based depth-map fusion; confidence-based refinement; confidence-weighted bundle optimization; corrupted depth maps; depth value; depth-map refinement system; pixel-wise confidence measurement; super-pixel-based planar propagation; Cameras; Color; Image sensors; Measurement; Optimization; Reliability; Sensors;
Conference_Titel :
Signal & Information Processing Association Annual Summit and Conference (APSIPA ASC), 2012 Asia-Pacific
Conference_Location :
Hollywood, CA
Print_ISBN :
978-1-4673-4863-8