Controlling Stroke Size in Fast Style Transfer with Recurrent Convolutional Neural Network

Abstract

Controlling stroke size in Fast Style Transfer remains a difficult task. So far, only a few attempts have been made towards it, and they still exhibit several deficiencies regarding efficiency, flexibility, and diversity. In this paper, we aim to tackle these problems and propose a recurrent convolutional neural subnetwork, which we call recurrent stroke‐pyramid, to control the stroke size in Fast Style Transfer. Compared to the state‐of‐the‐art methods, our method not only achieves competitive results with much fewer parameters but provides more flexibility and efficiency for generalizing to unseen larger stroke size and being able to produce a wide range of stroke sizes with only one residual unit. We further embed the recurrent stroke‐pyramid into the Multi‐Styles and the Arbitrary‐Style models, achieving both style and stroke‐size control in an entirely feed‐forward manner with two novel run‐time control strategies.

Controlling strokes in fast neural style transfer using content transforms

“…For explicit control over stroke sizes, Jing et al [17] propose a multibranch network architecture that is trained on multiple, discrete stroke sizes that are then encoded in a stroke pyramid in the network. Yang et al [45] extend the stroke pyramid to arbitrary style transfer. Yao et al [46] propose an arbitrary style transfer method that furthermore uses an attention-based mechanism for multi-stroke transfer.…”