Photorealistic Style Transfer

with Screened Poisson Equation

Roey Mechrez, Eli Shechtman and Lihi Zelnik-Manor


[Paper] [GitHub] [Results] [RealismNet Results]


Classic style-transfer methods take an input image (a) and a reference style image (b) and produce a stylized image (c), typically showing texture artifacts and missing details that make it look like a painting. Our method processes the stylized image (c) and makes it photo-realistic (d). The identity of the original image is preserved while the desired style is reliably transfered. The styled images were produced by StyleSwap [4] (top) and NeuralStyle [11] (bottom). Best seen enlarged on a full screen.



Recent work has shown impressive success in transferring painterly style to images. These approaches, however, fall short of photorealistic style transfer. Even when both the input and reference images are photographs, the output still exhibits distortions reminiscent of a painting. In this paper we propose an approach that takes as input a stylized image and makes it more photorealistic. It relies on the Screened Poisson Equation, maintaining the fidelity of the stylized image while constraining the gradients to those of the original input image. Our method is fast, simple, fully automatic and shows positive progress in making an image photorealistic. Our stylized images exhibit finer details and are less prone to artifacts.



“Photorealistic Style Transfer with Screened Poisson Equation”, to appear in BMVC 2017 [pdf] [BibTex] [Supplementary]


Try our code

Code to reporduce the experiments described in our paper is available in [GitHub]


Recent Related Work

Deep photo style transfer
Fujun Luan, Sylvain Paris, Eli Shechtman, and Kavita Bala In IEEE CVPR, 2017. [ProjectPage]