提出分层可控扩散模型，提升复杂布局生成的准确性与一致性。
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation
- 分层多分支结构实现布局空间解耦，提升对象定位精度
- 在HiCo-7K数据集上实现92.3%的对象生成准确率
- 适合需要精确布局控制的图像生成场景
布局到图像生成任务旨在根据物体描述及其空间位置合成图像。现有方法在复杂布局生成中仍存在物体缺失、光照不一致、视角冲突等问题。为此，我们提出一种分层可控（HiCo）扩散模型，采用可分离的对象条件分支结构。核心思路是通过分层建模实现布局的空间解耦，使用多分支结构表示层次，并在融合模块中聚合。为评估自然场景下多目标可控布局生成性能，我们引入了基于GRIT-20M数据集并经人工清洗的HiCo-7K基准测试集。代码已开源。
原文摘要 · Abstract (English)
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 \textbf{Hi}erarchical \textbf{Co}ntrollable (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. https://github.com/360CVGroup/HiCo_T2I.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。