Abstract by Samuel Giraud-Carrier
Retiming Smoke Simulation using Machine Learning
Art-directability is a crucial aspect of creating aesthetically pleasing
visual effects that help tell stories.
A particularly common method of art direction is the retiming of a simulation.
Unfortunately, the means of retiming an existing simulation sequence which
preserves the desired shapes is an ill-defined problem. Naively interpolating
values between frames leads to visual artifacts. Due to the difficulty in
formulating a proper interpolation method we elect to use a machine learning
approach to approximate this function. Our model is based on the ODE-net
structure and reproduces a set of desired time samples (in
our case equivalent to time steps) that achieves the desired new sequence speed, based on training from frames in the
original sequence. The flexibility
of the updated sequences' duration provided
by the time samples input makes this a visually effective and intuitively directable way to retime a simulation.