Learning Object Placement via Dual-path Graph Completion

TL;DR

This paper introduces a novel graph completion approach for object placement, modeling scenes as graphs and encoding foreground objects as special nodes, leading to improved placement plausibility and diversity.

Contribution

The paper proposes a dual-path graph completion module that effectively models scene context and object placement, advancing the state-of-the-art in object placement tasks.

Findings

Outperforms existing methods on OPA dataset

Generates more plausible object placements

Maintains diversity in placement options

Abstract

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.