OPAL-Net: A Generative Model for Part-based Object Layout Generation
This work addresses layout generation for objects in computer vision, but it appears incremental as it builds on existing methods like GCNs and VAEs.
The authors tackled the problem of generating part-based object layouts for multiple categories using a single model, achieving results that demonstrated versatility compared to baselines.
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.