Awesome-Sketch-Synthesis  by MarkMoHR

Paper collection for sketch synthesis (generation)

Created 6 years ago
531 stars

Top 59.8% on SourcePulse

GitHubView on GitHub
Project Summary

This repository is a curated collection of research papers and resources focused on sketch synthesis and vector graphics generation, primarily targeting researchers and practitioners in computer graphics and machine learning. It provides a structured overview of datasets, synthesis approaches, and generation techniques, aiming to serve as a comprehensive reference for the field.

How It Works

The collection is organized into several key areas: sketch synthesis approaches (e.g., concept-to-sketch, photo-to-sketch, text-to-sketch), vector graphics generation (2D and 3D), and art-to-sketch transformations (line art, rough sketches, manga). It categorizes papers by input modality, output type (vector vs. raster), and specific application domains, offering links to associated code, projects, and demos where available.

Quick Start & Requirements

This is a curated list of papers and does not involve direct installation or execution of code. Users are directed to individual paper repositories for specific requirements.

Highlighted Details

  • Comprehensive categorization of sketch synthesis methods, including semantic concept-to-sketch, photo-to-sketch, text/attribute-to-sketch, 3D shape-to-sketch, and art-to-sketch.
  • Extensive listing of datasets relevant to sketch synthesis, detailing vector stroke availability and paired photo data.
  • Coverage of both raster and vector graphics generation techniques, with a focus on recent advancements in diffusion models and transformer architectures for vector synthesis.
  • Inclusion of papers on 3D shape-to-sketch and various forms of art-to-sketch, such as manga and line art vectorization.

Maintenance & Community

The repository is maintained by MarkMoHR and encourages community contributions via pull requests or issues.

Licensing & Compatibility

The repository itself is likely under a permissive license (e.g., MIT, Apache) as it is a collection of links. However, the licenses of the linked papers and their associated codebases may vary significantly. Users must consult the licenses of individual projects.

Limitations & Caveats

This repository is a literature survey and does not provide executable code or a unified framework. Users must independently locate and evaluate the code for each cited paper. The rapidly evolving nature of the field means some links or projects may become outdated.

Health Check
Last Commit

5 days ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
9 stars in the last 30 days

Explore Similar Projects

Starred by Alex Yu Alex Yu(Research Scientist at OpenAI; Former Cofounder of Luma AI) and Sourabh Bajaj Sourabh Bajaj(Cofounder of Uplimit).

OmniSVG by OmniSVG

0.4%
2k
Multimodal SVG generator research paper leveraging VLMs
Created 5 months ago
Updated 1 month ago
Feedback? Help us improve.