Learning Object Placement via Dual-Path Graph Completion

Siyuan Zhou, Liu Liu, Li Niu, Liqing Zhang

ECCV 2022

doi:10.1007/978-3-031-19790-1_23 /eccv/2022/zhou2022eccv-learning/

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.

PDF ECCV Semantic Scholar

Cite

Text

Zhou et al. "Learning Object Placement via Dual-Path Graph Completion." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19790-1_23

Markdown

[Zhou et al. "Learning Object Placement via Dual-Path Graph Completion." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/zhou2022eccv-learning/) doi:10.1007/978-3-031-19790-1_23

BibTeX

@inproceedings{zhou2022eccv-learning,
  title     = {{Learning Object Placement via Dual-Path Graph Completion}},
  author    = {Zhou, Siyuan and Liu, Liu and Niu, Li and Zhang, Liqing},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2022},
  doi       = {10.1007/978-3-031-19790-1_23},
  url       = {https://mlanthology.org/eccv/2022/zhou2022eccv-learning/}
}