mlsanityData to 14 Oct 2026

Single-Line Drawing Generation via Semantics-Driven Optimization

arXiv 2606.01910 ↗First posted 1 Jun 2026cs.GR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Line drawings are a highly expressive art form that requires the artist to abstract and distill the essence of their subject. We present the first semantics-driven method for automatically generating single-line drawings in vector format, guided either by a text prompt describing the concept or an input image depicting it. Our approach leverages score distillation sampling to optimize the parameters of a uniform rational B-spline (URBS) curve, ensuring that the drawing consists of a single continuous stroke by design. This representation provides fine-grained control over the level of detail, while additional loss terms allow us to steer the final artistic style. We demonstrate that our method outperforms state-of-the-art text-to-image models and optimization pipelines for this task, producing results that are both more aesthetically pleasing and more faithful to the style of continuous line drawing artists. Furthermore, because our method generates a vectorized curve, it directly supports downstream fabrication processes such as embroidery, laser engraving and wire bending. Our code and results are available at https://github.com/tanguymagne/SLDgen.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 82 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

40 of 82 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  11. 2024Depth Anything V2cited by 1,422
  12. 2021Variational Diffusion Modelscited by 1,153
28 more
  1. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  2. 2017A Neural Representation of Sketch Drawingscited by 313
  3. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  4. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 187
  5. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Modelscited by 112
  6. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  7. 2022Learning to generate line drawings that convey geometry and semanticscited by 83
  8. 2020Sketchformer: Transformer-based Representation for Sketched Structurecited by 78
  9. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Modelcited by 76
  10. 2019Photo-Sketching: Inferring Contour Drawings from Imagescited by 68
  11. 2022CLIPascene: Scene Sketching with Different Types and Levels of Abstractioncited by 64
  12. 2023Word-As-Image for Semantic Typographycited by 63
  13. 2022CLIPasso: Semantically-Aware Object Sketchingcited by 57
  14. 2023DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Modelscited by 54
  15. 2023Breathing Life Into Sketches Using Text-to-Video Priorscited by 48
  16. 2018Learning to Sketch with Shortcut Cycle Consistencycited by 47
  17. 2020Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestaltcited by 42
  18. 20243Doodle: Compact Abstraction of Objects with 3D Strokescited by 21
  19. 2025SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generationcited by 14
  20. 2020Synthesizing human-like sketches from natural images using a conditional convolutional decodercited by 13
  21. 2019Teaching GANs to Sketch in Vector Formatcited by 8
  22. 2023Generative Escher Meshescited by 5
  23. 2020Repulsive Curvescited by 4
  24. 2025WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstractioncited by 4
  25. 2025Neural Image Abstraction Using Long Smoothing B-Splinescited by 4
  26. 2024SD-πXL: Generating Low-Resolution Quantized Imagery via Score Distillationcited by 3
  27. 2025CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Modelcited by 2
  28. 2025Image-driven Robot Drawing with Rapid Lognormal Movementscited by 1

Built on by

Not cited yet.