Geometry-Based Layout Generation with Hyper-Relations AMONG Objects

Recent studies show increasing demands and interests in automatic layout generation, while there is still much room for improving the plausibility robustness. In this paper, we present a data-driven generation framework without model formulation loss term optimization. We achieve organize priors directly based on samples from datasets instead of sampling probabilistic distributions. Therefore, our method enables expressing relations among three or more objects that are hard to be mathematically modeled. Subsequently, non-learning geometric algorithm proposed arrange considering constraints such as positions walls windows. Experiments outperforms state-of-the-art generated layouts competitive those designed by professionals.1