arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.08360cs.NEcs.AIcs.CVcs.LG
收藏

条件形态生成:通过神经细胞自动机实现结构数字的涌现生成

Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata

Ali Sakour

Ali Sakour

AI总结:

本文提出条件神经细胞自动机(c-NCA),通过局部规则和空间广播的类别向量生成MNIST数字,实现稳定的结构生成与生物鲁棒性。

摘要:

生物系统表现出显著的形态发生可塑性,其中单个基因组可以编码各种专门的细胞结构,这些结构由局部化学信号触发。在深度学习领域,可微神经细胞自动机(NCA)作为一种范式,被用来模仿这种自组织。然而,现有的NCA研究主要集中在连续纹理合成或单目标物体恢复上,留下了解决类别条件结构生成的挑战。在本工作中,我们提出了一种新颖的条件神经细胞自动机(c-NCA)架构,能够从单一通用种子生成不同的拓扑结构——具体来说是MNIST数字。该架构仅通过空间广播的类别向量引导生成。不同于传统生成模型(如GANs、VAEs)依赖于全局接收场,我们的模型强制执行严格的局部性和翻译等变性。我们证明,通过将一个one-hot条件注入到细胞感知场中,一组局部规则可以学习打破对称性并自组装成十个不同的几何吸引子。实验结果表明,我们的c-NCA实现了稳定的收敛,能够从单个像素正确生成数字拓扑,并表现出生物系统固有的鲁棒性。本工作弥合了基于纹理的NCA与结构模式形成之间的差距,提供了一种轻量、生物合理的方法用于条件生成。

英文摘要:

Biological systems exhibit remarkable morphogenetic plasticity, where a single genome can encode various specialized cellular structures triggered by local chemical signals. In the domain of Deep Learning, Differentiable Neural Cellular Automata (NCA) have emerged as a paradigm to mimic this self-organization. However, existing NCA research has predominantly focused on continuous texture synthesis or single-target object recovery, leaving the challenge of class-conditional structural generation largely unexplored. In this work, we propose a novel Conditional Neural Cellular Automata (c-NCA) architecture capable of growing distinct topological structures - specifically MNIST digits - from a single generic seed, guided solely by a spatially broadcasted class vector. Unlike traditional generative models (e.g., GANs, VAEs) that rely on global reception fields, our model enforces strict locality and translation equivariance. We demonstrate that by injecting a one-hot condition into the cellular perception field, a single set of local rules can learn to break symmetry and self-assemble into ten distinct geometric attractors. Experimental results show that our c-NCA achieves stable convergence, correctly forming digit topologies from a single pixel, and exhibits robustness characteristic of biological systems. This work bridges the gap between texture-based NCAs and structural pattern formation, offering a lightweight, biologically plausible alternative for conditional generation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑