# Laplacian-Steered Neural Style Transfer

arXiv: https://arxiv.org/abs/1707.01253 · HTML: https://mlsanity.com/paper/1707.01253/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2017.

## Built on by (most cited first, 18 of 18)

- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks](https://mlsanity.com/paper/2106.09249/) (2021)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation](https://mlsanity.com/paper/2309.03329/) (2023)
- [In the light of feature distributions: moment matching for Neural Style Transfer](https://mlsanity.com/paper/2103.07208/) (2021)
- [S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention](https://mlsanity.com/paper/2210.12381/) (2022)
- [FastCLIPstyler: Optimisation-free Text-based Image Style Transfer Using Style Representations](https://mlsanity.com/paper/2210.03461/) (2022)
- [Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization](https://mlsanity.com/paper/2208.01587/) (2022)
- [Evaluation in Neural Style Transfer: A Review](https://mlsanity.com/paper/2401.17109/) (2024)
- [Interactive Style Transfer: All is Your Palette](https://mlsanity.com/paper/2203.13470/) (2022)
- [Brain Surface Reconstruction from MRI Images Based on Segmentation Networks Applying Signed Distance Maps](https://mlsanity.com/paper/2104.04291/) (2021)
- [Arbitrary Style Transfer with Structure Enhancement by Combining the Global and Local Loss](https://mlsanity.com/paper/2207.11438/) (2022)
- [ColoristaNet for Photorealistic Video Style Transfer](https://mlsanity.com/paper/2212.09247/) (2022)
- [Edge Enhanced Image Style Transfer via Transformers](https://mlsanity.com/paper/2301.00592/) (2023)
- [PP-GAN : Style Transfer from Korean Portraits to ID Photos Using Landmark Extractor with GAN](https://mlsanity.com/paper/2306.13418/) (2023)
- [FEAT: Fashion Editing and Try-On from Any Design](https://mlsanity.com/paper/2605.02393/) (2026)
- [Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2610.09034/) (2026)

## Abstract (arXiv)

Neural Style Transfer based on Convolutional Neural Networks (CNN) aims to synthesize a new image that retains the high-level structure of a content image, rendered in the low-level texture of a style image. This is achieved by constraining the new image to have high-level CNN features similar to the content image, and lower-level CNN features similar to the style image. However in the traditional optimization objective, low-level features of the content image are absent, and the low-level features of the style image dominate the low-level detail structures of the new image. Hence in the synthesized image, many details of the content image are lost, and a lot of inconsistent and unpleasing artifacts appear. As a remedy, we propose to steer image synthesis with a novel loss function: the Laplacian loss. The Laplacian matrix ("Laplacian" in short), produced by a Laplacian operator, is widely used in computer vision to detect edges and contours. The Laplacian loss measures the difference of the Laplacians, and correspondingly the difference of the detail structures, between the content image and a new image. It is flexible and compatible with the traditional style transfer constraints. By incorporating the Laplacian loss, we obtain a new optimization objective for neural style transfer named Lapstyle. Minimizing this objective will produce a stylized image that better preserves the detail structures of the content image and eliminates the artifacts. Experiments show that Lapstyle produces more appealing stylized images with less artifacts, without compromising their "stylishness".