Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Open Access Articles
  3. MIT Open Access Articles
  4. SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation

SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation

Thumbnail Image
Download
Name

3721238.3730612.pdf

Size

23.55 MB

Format

Adobe PDF

Checksum (MD5)

f3688c498ec8717da70f34170c0a513d

Download all files submitted through automated deposit
3721238.3730612.zip (22.71 MB)
Author(s)
Arar, Ellie
•
Frenkel, Yarden
•
Cohen-Or, Daniel
•
Shamir, Ariel
•
Vinker, Yael
Date Issued
July 27, 2025
Publisher
ACM|Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers
Citation
Ellie Arar, Yarden Frenkel, Daniel Cohen-Or, Ariel Shamir, and Yael Vinker. 2025. SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation. In Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers (SIGGRAPH Conference Papers '25). Association for Computing Machinery, New York, NY, USA, Article 82, 1–12.
Version
Final published version
Abstract
Recent advancements in large vision-language models have enabled highly expressive and diverse vector sketch generation. However, state-of-the-art methods rely on a time-consuming optimization process involving repeated feedback from a pretrained model to determine stroke placement. Consequently, despite producing impressive sketches, these methods are limited in practical applications. In this work, we introduce SwiftSketch, a diffusion model for image-conditioned vector sketch generation that can produce high-quality sketches in less than a second. SwiftSketch operates by progressively denoising stroke control points sampled from a Gaussian distribution. Its transformer-decoder architecture is designed to effectively handle the discrete nature of vector representation and capture the inherent global dependencies between strokes. To train SwiftSketch, we construct a synthetic dataset of image-sketch pairs, addressing the limitations of existing sketch datasets, which are often created by non-artists and lack professional quality. For generating these synthetic sketches, we introduce ControlSketch, a method that enhances SDS-based techniques by incorporating precise spatial control through a depth-aware ControlNet. We demonstrate that SwiftSketch generalizes across diverse concepts, efficiently producing sketches that combine high fidelity with a natural and visually appealing style.
Description
SIGGRAPH Conference Papers ’25, Vancouver, BC, Canada
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
https://creativecommons.org/licenses/by/4.0/
Persistent DSpace Link
https://hdl.handle.net/1721.1/164741
DOI of Published Version
https://doi.org/10.1145/3721238.3730612
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.