Automated generation of 3D from 2D videos using Manifold Learning

Depth estimation from a single monocular image is a difficult problem.The task is even more challenging as depth cues such as motion, stereo correspondences are not present in single image. Hence machine learning based approach for extracting depth information from single image is proposed. Firstly depth is generated by manifold learning in which LLE algorithm is used, it is a non linear method of dimensionality reduction in which neighbors of input set in higher dimensional space are preserved while being transformed into lower dimensional space. The depth maps obtained are further refined by fixed point algorithm, it is supervised learning in which those features are extracted from image which have strong correspondences with labels.