内容感知的双视点立体图像缩放

Binocular stereo images retargeting based on content-aware

为适应不同立体显示终端多样化尺寸的需求,需要对某些尺寸一定的立体图像进行缩放调整.对于双视点的立体图像而言,需要考虑左右两视点的一致性问题,以及视差大小的问题.为此,将视差和匹配引入立体图像的尺寸调整,提出了一种基于Seam Carving的立体图像缩放算法.该算法在选择左视点缝隙时将匹配算法和视差融入其中,在缝隙的选择方面,通过提出新的能量函数做出更精确的选择,从而在调整图像大小的同时,达到了保持图像内容,调整视差大小的目的,并且保证了左右视点缝隙的一致性.

As far as the stereo images, the matching between the left and right image and the disparity should be considered, and the matching and the resizing of disparity are fused on the retargeting of the stereo images. A resizing method by using stereo extension of seam carving is proposed, which can keep the image content more precise during adjusting the size of the image, adjust the size of disparity, and ensure the consistency between the left and fight images.