The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing, inconsistent lighting, conflicting view angles, etc. To effectively address these issues, we propose a Hierarchical Controllable (HiCo) diffusion model for layout-to-image generation, featuring object seperable conditioning branch structure. Our key insight is to achieve spatial disentanglement through hierarchical modeling of layouts. We use a multi branch structure to represent hierarchy and aggregate them in fusion module. To evaluate the performance of multi-objective controllable layout generation in natural scenes, we introduce the HiCo-7K benchmark, derived from the GRIT-20M dataset and manually cleaned.
@misc{cheng2024hicohierarchicalcontrollablediffusion,
title={HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation},
author={Bo Cheng and Yuhang Ma and Liebucha Wu and Shanyuan Liu and Ao Ma and Xiaoyu Wu and Dawei Leng and Yuhui Yin},
year={2024},
eprint={2410.14324},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2410.14324},
}