MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
This addresses the need for flexible and category-aware object generation in computer vision, though it appears incremental as it builds on existing methods like Graph Convolutional Networks and Conditional Variational Autoencoders.
The paper tackled the problem of controllable, part-based generation of multi-category objects by introducing MeronymNet, a hierarchical approach that uses a unified model to generate objects from bounding box layouts to pixel-level depictions, resulting in superior performance scores compared to strong baselines and ablative variants.
We introduce MeronymNet, a novel hierarchical approach for controllable, part-based generation of multi-category objects using a single unified model. We adopt a guided coarse-to-fine strategy involving semantically conditioned generation of bounding box layouts, pixel-level part layouts and ultimately, the object depictions themselves. We use Graph Convolutional Networks, Deep Recurrent Networks along with custom-designed Conditional Variational Autoencoders to enable flexible, diverse and category-aware generation of 2-D objects in a controlled manner. The performance scores for generated objects reflect MeronymNet's superior performance compared to multiple strong baselines and ablative variants. We also showcase MeronymNet's suitability for controllable object generation and interactive object editing at various levels of structural and semantic granularity.