用递归模块构建自相似图像生成模型，提升生成质量。
Fractal Generative Models
- 将生成模型拆分为原子模块，递归组合成分形结构。
- 在像素级图像生成任务中表现优异，兼顾似然与质量。
- 适合对生成模型架构创新感兴趣的科研人员。
模块化是计算机科学的核心，将复杂函数抽象为基本单元。本文提出将生成模型抽象为原子生成模块，并通过递归调用构建新型生成模型，形成类似数学分形的自相似架构，称为分形生成模型。以自回归模型作为原子模块，在具有挑战性的逐像素图像生成任务上验证该框架，展现出出色的似然估计性能和生成质量。该工作或可开启生成建模新范式，为后续研究提供广阔空间。代码已开源：https://github.com/LTH14/fractalgen。
原文摘要 · Abstract (English)
Modularization is a cornerstone of computer science, abstracting complex functions into atomic building blocks. In this paper, we introduce a new level of modularization by abstracting generative models into atomic generative modules. Analogous to fractals in mathematics, our method constructs a new type of generative model by recursively invoking atomic generative modules, resulting in self-similar fractal architectures that we call fractal generative models. As a running example, we instantiate our fractal framework using autoregressive models as the atomic generative modules and examine it on the challenging task of pixel-by-pixel image generation, demonstrating strong performance in both likelihood estimation and generation quality. We hope this work could open a new paradigm in generative modeling and provide a fertile ground for future research. Code is available at https://github.com/LTH14/fractalgen.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。