A fused estimation method of depth based on depth from stereo and depth from focus

Depth from stereo and depth from focus are two classical image-based 3D reconstruction methods, which have distinct advantages in different applications respectively. In this paper, we propose a fused depth recovery method based on depth from stereo and depth from focus. First, we choose some depth candidates using depth from stereo method. Then, a weighted linear cost function is employed to determine the final depth. As we know, depth from stereo and depth from focus need different kinds of input images, which can not be acquired at the same time by using traditional imaging system. We have preliminary tackled this issue by using a camera array system and synthetic aperture photography. Experiment results have verified the validity and advantages of proposed method.