# Deep Photo Style Transfer

arXiv: https://arxiv.org/abs/1703.07511 · HTML: https://mlsanity.com/paper/1703.07511/

## Key facts

- Cited by 168 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2017.

## Built on by (most cited first, 30 of 168)

- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023)
- [ARF: Artistic Radiance Fields](https://mlsanity.com/paper/2206.06360/) (2022)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [NeRF for Outdoor Scene Relighting](https://mlsanity.com/paper/2112.05140/) (2021)
- [Measuring Style Similarity in Diffusion Models](https://mlsanity.com/paper/2404.01292/) (2024)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Expressive Text-to-Image Generation with Rich Text](https://mlsanity.com/paper/2304.06720/) (2023)
- [Enhancing Photorealism Enhancement](https://mlsanity.com/paper/2105.04619/) (2021)
- [The Spatially-Correlative Loss for Various Image Translation Tasks](https://mlsanity.com/paper/2104.00854/) (2021)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [MagicMix: Semantic Mixing with Diffusion Models](https://mlsanity.com/paper/2210.16056/) (2022)
- [High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network](https://mlsanity.com/paper/2105.09188/) (2021)
- [SSH: A Self-Supervised Framework for Image Harmonization](https://mlsanity.com/paper/2108.06805/) (2021)
- [Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches](https://mlsanity.com/paper/2207.04718/) (2022)
- [LightIt: Illumination Modeling and Control for Diffusion Models](https://mlsanity.com/paper/2403.10615/) (2024)
- [Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation](https://mlsanity.com/paper/2102.01187/) (2021)
- [Self-supervised Outdoor Scene Relighting](https://mlsanity.com/paper/2107.03106/) (2021)
- [BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation](https://mlsanity.com/paper/2110.11728/) (2021)
- [UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene](https://mlsanity.com/paper/2208.07059/) (2022)
- [Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts](https://mlsanity.com/paper/2104.00887/) (2021)
- [CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer](https://mlsanity.com/paper/2207.04808/) (2022)
- [Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2108.04547/) (2021)
- [Face Relighting with Geometrically Consistent Shadows](https://mlsanity.com/paper/2203.16681/) (2022)
- [Towards High Fidelity Face Relighting with Realistic Shadows](https://mlsanity.com/paper/2104.00825/) (2021)
- [Domain-Aware Universal Style Transfer](https://mlsanity.com/paper/2108.04441/) (2021)
- [Image-Based CLIP-Guided Essence Transfer](https://mlsanity.com/paper/2110.12427/) (2021)
- [Language-Driven Image Style Transfer](https://mlsanity.com/paper/2106.00178/) (2021)

## Abstract (arXiv)

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.