SketchBloom expands sparse sketches into detailed editable vector art

SketchBloom: Training-Free Vector Sketch Outpainting with Stroke-Level Style Control

Computer Vision and Pattern Recognition

Summary

Drawing more of a simple sketch while keeping the style and lines consistent is hard. The authors created SketchBloom, a tool that extends sketches without needing new training. It uses existing image outpainting and style transfer methods combined with special stroke controls to create detailed, editable vector drawings. This means you can add new parts to your sketch that match the original style and can still be adjusted easily.

What this means in practice

  • For digital artists: Extend incomplete line sketches into detailed editable vector artwork that preserves original stroke style without retraining models.
  • For graphic design software developers: Integrate sketch outpainting that produces style-consistent vector outputs, enabling advanced vector editing features from sparse inputs.

Authors

Quang-Thinh Nguyen, Duy-Khang Do, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le

Abstract

Outpainting sparse sketches while preserving contour coherence and stroke style remains challenging. We present SketchBloom, a training-free framework that combines pretrained raster outpainting and style-transfer guidance with per-instance vector optimization. Given a sketch, a scene prompt, and an optional reference style, it produces an editable Scalable Vector Graphic (SVG) composed of Bezier strokes. Adaptive latent blending balances content contours and reference texture without model retraining. A reference-derived stroke vocabulary initializes contour- and DINO-attention-guided strokes, which are optimized separately for structure and texture before contour-emphasizing multiply fusion. As in prior optimization-based vector sketching, no task-specific network is trained; our contribution is the synthesis design specialized to sketch outpainting. On LineArtOut-1K, comprising 1,024 input and style combinations, SketchBloom improves perceptual, semantic, and structural fidelity over the evaluated vector baselines when all methods vectorize the same outpainted raster. This protocol evaluates vector synthesis rather than end-to-end outpainting or reference-style superiority. Runtime is approximately six minutes per pair on a single NVIDIA H200 GPU. Project page: https://khangcntn123.github.io/SketchBloom/