This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
There are methods implemented based on learning features, visual cues. You can refer to paper 3-D Reconstruction from a Single Still Image here. Using this method they have created qualitatively correct 3-d models for 64.9% of 588 images downloaded from the internet, and also extended model to produce large scale 3d models from a few images
