Clustered Vector Textures

ACM Transactions on Graphics (Proc. SIGGRAPH), 2022

Given a small input exemplar (left), our method synthesizes a larger output result (right).
Fast forward

Supplementary video



Repetitive vector patterns are common in a variety of applications but can be challenging and tedious to create. Existing automatic synthesis methods target relatively simple, unstructured patterns such as discrete elements and continuous Bézier curves. This paper proposes an algorithm for generating vector patterns with diverse shapes and structured local interactions via a sample-based representation. Our main idea is adding explicit clustering as part of neighborhood similarity and iterative sample optimization for more robust sample synthesis and pattern reconstruction. The results indicate that our method can significantly outperform existing methods on synthesizing a variety of structured vector textures.

Resources and Downloads

  • Paper

  • Code


 title = {Clustered Vector Textures},
 author = {Peihan Tu and Li-Yi Wei and Matthias Zwicker},
 journal = {ACM Trans. Graph.},
 volume = {41},
 number = {4},
 articleno = {159},
 doi = {10.1145/3528223.3530062},
 year = 2022,
 month = 7,


For questions and clarifications, please get in touch with:
Peihan Tu

Template from GVV Group at MPI.