Learning Object Placement via Dual-path Graph Completion
This work addresses object placement for image composition, which is an incremental improvement in a specific domain.
The paper tackles the problem of object placement by treating it as a graph completion task, proposing a novel graph completion module and dual-path framework, and demonstrates significant outperformance over existing methods on the OPA dataset in generating plausible placements without losing diversity.
Object placement aims to place a foreground object over a background image with a suitable location and size. In this work, we treat object placement as a graph completion problem and propose a novel graph completion module (GCM). The background scene is represented by a graph with multiple nodes at different spatial locations with various receptive fields. The foreground object is encoded as a special node that should be inserted at a reasonable place in this graph. We also design a dual-path framework upon the structure of GCM to fully exploit annotated composite images. With extensive experiments on OPA dataset, our method proves to significantly outperform existing methods in generating plausible object placement without loss of diversity.