SIGGRAPH Asia 2026

SketchFlow

Zero-Shot Vector Sketch Generation via GMM Prior Flow in CLIP Latent Space

Shenzhen University
SketchFlow generations of letters, numbers, landmarks, characters, emotions, and poses

SketchFlow generates open-vocabulary vector sketches while preserving sparse, human-like stroke trajectories.

Abstract

Vector sketches are a concise medium for abstract human expression, yet high-quality text-to-sketch pairs are scarce. SketchFlow formulates cross-modal alignment as a continuous mapping problem in CLIP latent space. It expands discrete category text embeddings into a continuous Gaussian Mixture Model prior, then learns an Optimal Transport Conditional Flow Matching vector field that transports this prior to the rendered-sketch feature distribution. A hybrid diffusion decoder combining a 1D U-Net and Transformer decodes the transported features into vector stroke trajectories. Trained from category-only QuickDraw sketches, SketchFlow supports fast zero-shot synthesis for open-vocabulary concepts, semantic modifiers, and continuous concept interpolation.

Method

SketchFlow method overview

01

Continuous GMM Prior

Noise around category text embeddings expands isolated semantic anchors into a continuous source distribution.

02

OT-CFM Transport

A learned vector field transports the GMM prior toward the rendered-sketch manifold in CLIP space.

03

Vector Decoding

A hybrid 1D U-Net and Transformer diffusion decoder generates ordered 256-point stroke trajectories.

345 QuickDraw categories
~50M human-drawn sketches
256 points per trajectory
ViT-B/32 shared CLIP space

Open-Vocabulary Results

Drawing Process

Each animation follows the generated vector trajectory from its first point to the completed sketch.

SIGGRAPH

8 generated trajectories
Generated letter S Generated letter I Generated letter G Generated letter G Generated letter R Generated letter A Generated letter P Generated letter H

ASIA 2026

8 generated trajectories
Generated letter A Generated letter S Generated letter I Generated letter A Generated digit 2 Generated digit 0 Generated digit 2 Generated digit 6

Malaysia Landmarks

6 generated trajectories
Generated Malaysia landmark 1 Generated Malaysia landmark 2 Generated Malaysia landmark 3 Generated Malaysia landmark 4 Generated Malaysia landmark 5 Generated Malaysia landmark 6

Scope and Limitations

SketchFlow is trained from the 345 discrete QuickDraw categories. It is not a general image model and does not reliably parse long, compositional prompts. Its strongest zero-shot behavior appears on concise, visually distinctive concepts that CLIP represents clearly, such as Kirby, Mickey, ghosts, rockets, emotions, symbols, and landmarks. Generation remains stochastic, so sampling multiple candidates can be useful.

BibTeX

@inproceedings{zhou2026sketchflow,
  title     = {SketchFlow: Zero-Shot Vector Sketch Generation
               via GMM Prior Flow in CLIP Latent Space},
  author    = {Zhou, Jin and Yang, Hongliang and
               Xu, Pengfei and Huang, Hui},
  booktitle = {ACM SIGGRAPH Asia 2026 Conference Papers},
  year      = {2026}
}