Deep Photo Style Transfer

03/22/2017
by   Fujun Luan, et al.
1

This paper introduces a deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style. Our approach builds upon the recent work on painterly transfer that separates style from the content of an image by considering different layers of a neural network. However, as is, this approach is not suitable for photorealistic style transfer. Even when both the input and reference images are photographs, the output still exhibits distortions reminiscent of a painting. Our contribution is to constrain the transformation from the input to the output to be locally affine in colorspace, and to express this constraint as a custom fully differentiable energy term. We show that this approach successfully suppresses distortion and yields satisfying photorealistic style transfers in a broad variety of scenarios, including transfer of the time of day, weather, season, and artistic edits.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

page 8

research
07/01/2018

Photorealistic Style Transfer for Videos

Photorealistic style transfer is a technique which transfers colour from...
research
07/24/2019

One-Shot Mutual Affine-Transfer for Photorealistic Stylization

Photorealistic style transfer aims to transfer the style of a reference ...
research
09/28/2017

Photorealistic Style Transfer with Screened Poisson Equation

Recent work has shown impressive success in transferring painterly style...
research
07/10/2020

Geometric Style Transfer

Neural style transfer (NST), where an input image is rendered in the sty...
research
01/10/2020

Network of Steel: Neural Font Style Transfer from Heavy Metal to Corporate Logos

We introduce a method for transferring style from the logos of heavy met...
research
01/15/2019

Image Synthesis and Style Transfer

Affine transformation, layer blending, and artistic filters are popular ...
research
05/19/2021

Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics

Current deep learning techniques for style transfer would not be optimal...

Please sign up or login with your details

Forgot password? Click here to reset