Virtual Cinematography Using Optimization and Temporal Smoothing
The problem of automatic virtual cinematography is often approached as an optimization problem. By identifying the extrema of an objective function matching some desired parameters, such as those common in live action photography or cinematography, a suitable camera pose or path can be automatically determined. With several constraints on function form, multiple objective functions can be combined into a single optimizable function, which can be further extended to model the smoothness of the found camera path using an active contour model. Finally, these virtual cinematographic techniques can be used to find paths in either live or scripted scenes with relatively low computational cost.