{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/m-nca-texture-generation-with-ultra-compact","title":"$μ$NCA: Texture Generation with Ultra-Compact Neural Cellular Automata","arxiv_id":"2111.13545","date":"2021-11-26","proceeding":null,"authors":["Alexander Mordvintsev","Eyvind Niklasson"],"abstract":"We study the problem of example-based procedural texture synthesis using highly compact models. Given a sample image, we use differentiable programming to train a generative process, parameterised by a recurrent Neural Cellular Automata (NCA) rule. Contrary to the common belief that neural networks should be significantly over-parameterised, we demonstrate that our model architecture and training procedure allows for representing complex texture patterns using just a few hundred learned parameters, making their expressivity comparable to hand-engineered procedural texture generating programs. The smallest models from the proposed $\\mu$NCA family scale down to 68 parameters. When using quantisation to one byte per parameter, proposed models can be shrunk to a size range between 588 and 68 bytes. Implementation of a texture generator that uses these parameters to produce images is possible with just a few lines of GLSL or C code.","url_abs":"https://arxiv.org/abs/2111.13545v1","url_pdf":"https://arxiv.org/pdf/2111.13545v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"m-nca-texture-generation-with-ultra-compact","repo_url":"https://github.com/google-research/self-organising-systems/tree/master/notebooks/","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"m-nca-texture-generation-with-ultra-compact","repo_url":"https://github.com/google-research/self-organising-systems/blob/master/notebooks/%CE%BCNCA_jax.ipynb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"m-nca-texture-generation-with-ultra-compact","repo_url":"https://github.com/google-research/self-organising-systems/blob/master/notebooks/%CE%BCNCA_pytorch.ipynb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"c-code","task_name":"C++ code"},{"task_slug":"texture-synthesis","task_name":"Texture Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.13545","atlas_url":"https://app.syntology.ai/?focus=2111.13545","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}