Perceptual Losses for Real-Time Style Transfer and Super-Resolution
This addresses the problem of slow image style transfer for users needing real-time applications, though it is incremental by combining existing approaches.
The paper tackles image transformation tasks by training feed-forward convolutional neural networks with perceptual loss functions instead of per-pixel losses, achieving real-time style transfer with results similar to optimization-based methods but three orders of magnitude faster and improving super-resolution visual quality.
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a \emph{per-pixel} loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing \emph{perceptual} loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image transformation tasks. We show results on image style transfer, where a feed-forward network is trained to solve the optimization problem proposed by Gatys et al in real-time. Compared to the optimization-based method, our network gives similar qualitative results but is three orders of magnitude faster. We also experiment with single-image super-resolution, where replacing a per-pixel loss with a perceptual loss gives visually pleasing results.