Sketch-to-Art: Synthesizing Stylized Art Images From Sketches

Bingchen Liu, Kunpeng Song, Ahmed Elgammal
2/26/2020
cs.CVeess.IV

Official code: bingchenlll/Sketch2art-pytorch (10 stars, last commit 2020-09-24).

Abstract

We propose a new approach for synthesizing fully detailed art-stylized images from sketches. Given a sketch, with no semantic tagging, and a reference image of a specific style, the model can synthesize meaningful details with colors and textures. The model consists of three modules designed explicitly for better artistic style capturing and generation. Based on a GAN framework, a dual-masked mechanism is introduced to enforce the content constraints (from the sketch), and a feature-map transformation technique is developed to strengthen the style consistency (to the reference image). Finally, an inverse procedure of instance-normalization is proposed to disentangle the style and content information, therefore yields better synthesis performance. Experiments demonstrate a significant qualitative and quantitative boost over baselines based on previous state-of-the-art techniques, adopted for the proposed process.

View on arXivView PDF

Code Implementations(1)

bingchenlll/Sketch2art-pytorchOfficial100%

The pytorch implementation of the paper: Sketch-to-Art: Synthesizing Stylized Art Images From Sketches

100PythonSep 24, 20206 years ago

Similar Papers

Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation

86% match1 repo282023

Multi-Style Facial Sketch Synthesis through Masked Generative Modeling

86% match2024

CustomSketching: Sketch Concept Extraction for Sketch-based Image Synthesis and Editing

86% match2024

PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptation

86% match2024

Stylized Face Sketch Extraction via Generative Prior with Limited Data

85% match1 repo752024

Text to Sketch Generation with Multi-Styles

85% match1 repo112025

Cite this paper

@article{liu2020sketchtoart,
  title  = {Sketch-to-Art: Synthesizing Stylized Art Images From Sketches},
  author = {Bingchen Liu and Kunpeng Song and Ahmed Elgammal},
  year   = {2020},
  eprint = {2002.12888},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2002.12888}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2002.12888.svg)](https://codeofpaper.com/paper/2002.12888)

Discussion