GTLayout: Learning General Trees for Structured Grid Layout Generation

Structured grid layouts are preferable in many scenarios of 2D visual content creation since their structures facilitate further layout editing. Multiple geometry-based methods can effectively create structured grid layouts but require user-provided constraints or rules. Existing data-driven approaches have achieved remarkable performance on layout generation, but fail to produce appropriate layout structures. We present GTLayout, a novel generative model for structured grid layout generation. We adopt general trees to represent structured grid layouts and exploit a recursive neural network (RvNN) for this generation task. Our model can handle grid layouts with varied structures and regular arrangements. Qualitative and quantitative experiments on public grid layout datasets show that our method outperforms several baselines in the tasks of layout reconstruction and layout generation, especially when the datasets contain a small number of samples. We also demonstrate that the structured layout space constructed by our method enables structure blending between structured layouts. We will release our code upon the acceptance of the paper.