As humans,we perceive the three-dimensional structure of the planet around us with apparent ease. Think of how vivid the three-dimensional percept is once you check out a vase of flowers sitting on the table next to you. You can tell the form and translucency of every petal through the subtle patterns of sunshine and shading that play across its surface and effortlessly segment each flower from the background of the scene The forward models that we use in computer vision are usually developed in physics (radiometry, optics, and sensor design) and in computer graphics . Both of these fields model how objects move and animate, how light reflects off their surfaces, is scattered by the atmosphere, refracted through camera lenses (or human eyes), and finally projected onto a flat (or curved) image plane. While computer graphics aren't yet perfect (no fully computer animated movie with human characters has yet succeeded at crossing the uncanny valley2 that separates real humans from...