According to CNET , researchers from the University of Carnegie Mellon have developed a technology that allows them to make flat objects in a photo three-dimensional, and freely manipulate them.
The technology is based on using the stock base of 3D models of objects from everyday life (cars, furniture, clothing, utensils ...).
After a little adjustment and calibration, the system allows you to replace the flat object from the photo with its volumetric version, which can be freely rotated in space and animated.
')
At the moment there are difficulties associated with filling the database of models. In many cases, you have to use a close, but not identical in geometry model for the object being modified.
As the model database is filled, the system will allow you to quickly recognize objects and replace them with exact 3D models.
At this stage, there are also difficulties with “pulling out” of objects with jagged edges, or located on a heterogeneous background.
The technology will be presented at the SIGGRAPH 2014 conference, August 13, in Vancouver.