Image-based view synthesis by combining trilinear tensors and learning techniques

@inproceedings{Avidan1997ImagebasedVS,
  title={Image-based view synthesis by combining trilinear tensors and learning techniques},
  author={Shai Avidan and Theodoros Evgeniou and Amnon Shashua and Tomaso A. Poggio},
  booktitle={VRST},
  year={1997}
}
We present a new method for rendering novel images of flexible 3D objects from a small number of example images in correspondence. The strength of the method is the ability to synthesize images whose viewing position is significantly far away from the viewing cone of the example images (“view extrapolation”), yet without ever modeling the 3D structure of the scene. The method relies on synthesizing a chain of “trilinear tensors” that gov erns the warping function from the example images to the… CONTINUE READING