Researchers Tao Chen, Zhe Zhu, Ariel Shamir, Shi-Min Hu and Daniel Cohen-Or have developed a software called 3-Sweep
that can extract editable 3D data from a 2D image.
It's not the usual software that makes you walk around an object and fire off a dozen shots. It's all about one single image and you no longer have to be there with a camera. Instead, it's an interactive technique for manipulating simple 3D shapes based on extracting them from a single photograph. You basically pull a 2D image from anywhere, and quickly create a model of it.
"Our approach combines the cognitive abilities of humans with the computational accuracy of the machine to solve this problem,"
writes the team. What you basically do is use your mouse to "sweep" lines and/or ellipses across the image, quickly teaching the software where the axes are.
It definitely seems an interesting breakthrough! For those of you in Hong Kong, a 3-Sweep
demo is scheduled for the upcoming SIGGRAPH Asia.