Adaptive image-space stereo view synthesis

Stereo vision is becoming increasingly popular in feature films, visualization and interactive applications such as computer games. However, computation costs are doubled when rendering an individual image for each eye. In this work, we propose to only render a single image, together with a depth buffer and use image-based techniques to generate two individual images for the left and right eye. The resulting method computes a high-quality stereo pair for roughly half the cost of the traditional methods. We achieve this result via an adaptive-grid warping that also involves information from previous frames to avoid artifacts.

@InProceedings { DREMS10a,
  author       = "Didyk, Piotr and Ritschel, Tobias and Eisemann, Elmar and Myszkowski, Karol and Seidel, Hans-Peter",
  title        = "Adaptive image-space stereo view synthesis",
  booktitle    = "Vision, Modeling and Visualization Workshop",
  pages        = "299--306",
  year         = "2010",
  address      = "Siegen, Germany",
  url          = "http://graphics.tudelft.nl/Publications-new/2010/DREMS10a"
}