将图像生成的中间特征拆解为可解释的局部模式，实现精准可控的图像合成。
Disentangling Regional Primitives for Image Generation
- 从特征完备性、空间有限性和一致性出发，定义生成网络的表征结构
- 通过哈桑尼交互计算出可独立控制的局部图像模式组件
- 揭示图像生成本质是多个局部模式叠加，适合可控生成与模型分析
本文从新视角解析图像生成神经网络的表征结构。提出特征完备性、空间有界性和一致性三项理想属性，用以定义生成模型的表征结构。基于这些属性，提出一种方法，从中间层特征中解耦出原始特征组件，每个组件生成覆盖多个图像块的局部模式。整个图像的生成可被解释为这些特征组件的线性叠加。证明满足特征完备性和线性可加性的特征组件，可计算为或（OR）哈桑尼交互。实验验证了解耦出的原始区域模式具有高保真度。
原文摘要 · Abstract (English)
This paper explains a neural network for image generation from a new perspective, i.e., explaining representation structures for image generation. We propose a set of desirable properties to define the representation structure of a neural network for image generation, including feature completeness, spatial boundedness and consistency. These properties enable us to propose a method for disentangling primitive feature components from the intermediate-layer features, where each feature component generates a primitive regional pattern covering multiple image patches. In this way, the generation of the entire image can be explained as a superposition of these feature components. We prove that these feature components, which satisfy the feature completeness property and the linear additivity property (derived from the feature completeness, spatial boundedness, and consistency properties), can be computed as OR Harsanyi interaction. Experiments have verified the faithfulness of the disentangled primitive regional patterns.
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。