Style Transfer for Light Field Photography
This work addresses a domain-specific need for light field photography, offering an incremental adaptation of existing methods to handle unique data constraints.
The paper tackled the problem of applying neural style transfer to light field images, which lack existing feed-forward networks due to small datasets, by proposing a method that adapts pre-trained monocular networks through iterative backpropagation to stylize each view while maintaining consistency.
As light field images continue to increase in use and application, it becomes necessary to adapt existing image processing methods to this unique form of photography. In this paper we explore methods for applying neural style transfer to light field images. Feed-forward style transfer networks provide fast, high-quality results for monocular images, but no such networks exist for full light field images. Because of the size of these images, current light field data sets are small and are insufficient for training purely feed-forward style-transfer networks from scratch. Thus, it is necessary to adapt existing monocular style transfer networks in a way that allows for the stylization of each view of the light field while maintaining visual consistencies between views. Instead, the proposed method backpropagates the loss through the network, and the process is iterated to optimize (essentially overfit) the resulting stylization for a single light field image alone. The network architecture allows for the incorporation of pre-trained fast monocular stylization networks while avoiding the need for a large light field training set.