TL;DR
MeronymNet is a hierarchical, controllable model for multi-category object generation that uses a guided coarse-to-fine approach with graph and recurrent networks, outperforming baselines and enabling detailed editing.
Contribution
It introduces a unified hierarchical framework combining GCNs, RNNs, and VAEs for flexible, category-aware object generation and editing.
Findings
Superior performance over strong baselines
Effective controllable object editing
Versatile multi-category object generation
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
