本发明结合了多尺度CNN和连续CRF优化思想,不仅能够以较高的精确度估计出深度图,又能使得到的深度图轮廓清晰;本发明所估计的深度有比较高的分辨率,而且所得到的深度图能保留场景中所有对象的深度细节信息,具有更好的视觉效果. The present invention combines the multi-scale and continuous CRF CNN optimization ...
A depth estimation method for a monocular image based on a multi-scale CNN and a continuous CRF is disclosed in this invention. A CRF module is adopted to calculate a unary potential energy according to the output depth map of a DCNN, and the pairwise sparse potential energy according to ...
According to the method, optimized thoughts of multi-scale CNN and continuous CRF are combined, so that not only a depth map can be estimated with a relatively high precision, the contour of the obtained depth map can also be clear. The depth estimated by means of the method has a ...