论文标题
蛋白石网络：基于部分对象布局生成的生成模型
OPAL-Net: A Generative Model for Part-based Object Layout Generation
论文作者
论文摘要
我们建议使用单个统一模型从多个类别中进行基于部分的对象生成的新型层次结构Opal-Net。我们采用了一种粗到最新的策略，该策略涉及对象的框架布局和像素级的零件布局的自动回归产生。我们使用图形卷积网络，深度循环网络以及定制设计的条件变异自动编码器来启用对象布局的灵活，多样化和类别感知的生成。我们在Pascal-Parts数据集上训练蛋白石网。生成的样品和相应的评估得分证明了与消融性变体和基准相比，蛋白石网络的多功能性。
We propose OPAL-Net, a novel hierarchical architecture for part-based layout generation of objects from multiple categories using a single unified model. We adopt a coarse-to-fine strategy involving semantically conditioned autoregressive generation of bounding box layouts and pixel-level part layouts for objects. We use Graph Convolutional Networks, Deep Recurrent Networks along with custom-designed Conditional Variational Autoencoders to enable flexible, diverse and category-aware generation of object layouts. We train OPAL-Net on PASCAL-Parts dataset. The generated samples and corresponding evaluation scores demonstrate the versatility of OPAL-Net compared to ablative variants and baselines.
