to appear in CVPR 2014, Colombus, OH.
We propose a technique to use the structural information extracted from a set of 3D models of an object class to improve novel-view synthesis for images showing unknown instances of this class. These novel views can be used to ``amplify'' training image collections that typically contain only a low number of views or lack certain classes of views entirely (eg. top views).
We extract the correlation of position, normal, reflectance and appearance from computer-generated images of a few exemplars and use this information to infer new appearance for new instances. We show that our approach can improve performance of state-of-the-art detectors using real-world training data. Additional applications include guided versions of inpainting, 2D-to-3D conversion, super-resolution and non-local smoothing.
This work was supported by the ERC grand Cognimund