morelike22.PNG

TEXTURE SYNTHESIS

Multiresolution Stochastic Texture Synthesis is a non-parametric example-based algorithm for image generation we developed at Embark Studios. This was our first exploration of automatically extracting rules from examples. See this Medium blog post for more details around the concept and why we believe it is awesome and a logical evolution of procedural systems. For more technical details, please see this NordicGames2020 talk: "More Like This, Please! Texture Synthesis and Remixing from a Single Example".

IT'S OPENSOURCE!

Did I mention it is opensource? It's opensource :) See our github page

1_dCGRxQnC6Ul7SpolxN19cA (1).png

WHAT CAN IT DO?

1) Generate similar-looking images from a single example image.

68747470733a2f2f692e696d6775722e636f6d2f

2) We can also provide multiple example images and the algorithm will "remix" them into a new image.

68747470733a2f2f692e696d6775722e636f6d2f

3) We can also guide the generation by providing a transformation "FROM"-"TO" in a form of guide maps

68747470733a2f2f692e696d6775722e636f6d2f

4) We can auto-generate example guide maps, which produces a style transfer-like effect.

68747470733a2f2f692e696d6775722e636f6d2f

5) We can fill-in missing information with inpaint.

68747470733a2f2f692e696d6775722e636f6d2f

6) Make non-tiling textures tile.

68747470733a2f2f692e696d6775722e636f6d2f

7) We can also combine multiple modes together. For example, multi-example guided synthesis:

68747470733a2f2f692e696d6775722e636f6d2f

Or chaining multiple stages of generation together:

68747470733a2f2f692e696d6775722e636f6d2f

WHAT IT CANNOT DO

  • Struggles with complex semantics beyond pixel color (unless you guide it)

  • Not great with regular textures (seams can become obvious)

  • Cannot infer new information from existing information (only operates on what’s already there)

  • Designed for single exemplars or very small datasets (unlike Deep Learning based approaches)

REFERENCES

[1] [Opara & Stachowiak] "More Like This, Please! Texture Synthesis and Remixing from a Single Example"

[2] [Harrison] Image Texture Tools

[3] [Ashikhmin] Synthesizing Natural Textures

[4] [Efros & Leung] Texture Synthesis by Non-parametric Sampling

[5] [Wey & Levoy] Fast Texture Synthesis using Tree-structured Vector Quantization

[6] [De Bonet] Multiresolution Sampling Procedure for Analysis and Synthesis of Texture Images

‚Äč

© by Anastasia Opara