无需训练的物体-背景组合性T2I通过动态空间引导和多路径剪枝
Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
AI总结：
本文提出无需训练的框架，通过动态空间引导和多路径剪枝，提升文本到图像扩散模型中背景与物体的组合性与平衡性。
摘要：
现有文本到图像扩散模型在主体合成方面表现优异，但存在持续的前景偏差，将背景视为被动且未优化的副产品。这种不平衡损害了全局场景连贯性并限制了组合控制。为此，我们提出一个无需训练的框架，重新组织扩散采样以显式考虑前景-背景交互。我们的方法包括两个关键组件。首先，动态空间引导引入一种软的、时间步依赖的门控机制，在扩散过程中调节前景和背景的注意力，实现空间平衡的生成。其次，多路径剪枝执行多路径潜在探索，并利用内部注意力统计和外部语义对齐信号动态过滤候选轨迹，保留更符合物体-背景约束的轨迹。我们进一步开发了一个专门用于评估物体-背景组合性的基准。在多个扩散基础架构上的广泛评估显示，背景连贯性和物体-背景组合性对齐性均得到一致提升。
英文摘要：
Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global scene coherence and constrains compositional control. To address the limitation, we propose a training-free framework that restructures diffusion sampling to explicitly account for foreground-background interactions. Our approach consists of two key components. First, Dynamic Spatial Guidance introduces a soft, time step dependent gating mechanism that modulates foreground and background attention during the diffusion process, enabling spatially balanced generation. Second, Multi-Path Pruning performs multi-path latent exploration and dynamically filters candidate trajectories using both internal attention statistics and external semantic alignment signals, retaining trajectories that better satisfy object-background constraints. We further develop a benchmark specifically designed to evaluate object-background compositionality. Extensive evaluations across multiple diffusion backbones demonstrate consistent improvements in background coherence and object-background compositional alignment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
