Single-Line Drawing Generation via Semantics-Driven Optimization
This work addresses the challenge of automatically creating single-line vector art, a task previously unsolved, enabling downstream applications in digital art and fabrication.
This paper introduces the first semantics-driven method for generating single-line drawings in vector format from text prompts or images, using score distillation sampling to optimize a B-spline curve. The method outperforms existing text-to-image models in aesthetic quality and style faithfulness, and directly supports fabrication processes like embroidery and laser engraving.
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.