Dynamic-Net: Tuning the Objective Without Re-Training for Synthesis Tasks

We propose an approach that enables traversing the "objective-space", spanned by two different objectives, at test-time, without re-training, as illustrated by the blue dot moving along the blue curve in the plot. This is different from the common practice of training a separate network for each objective, represented by ×'s on the plot. Using a single Dynamic-Net we can tune the level of stylization of an image, monitor completion quality per image, or control facial attributes, all interactively at test-time, without re-training. [Animated figure, please view in Acrobat Reader].