基于锚点条件的景观图像生成组合控制
Anchor-Conditioned Compositional Control for Landscape Image Generation
AI总结：
提出锚点条件微调框架，通过解耦交叉注意力机制注入四维组合锚点向量，实现景观图像生成中的组合控制，在水平线检测和三分法对齐上取得最优性能。
摘要：
图像生成模型虽然被广泛用作创意工具，但对摄影师和视觉艺术家常规执行的组合控制类型支持有限。本文提出了一个用于景观图像生成的锚点条件微调框架的早期结果，其中从训练图像中提取四维组合锚点向量，并通过带有傅里叶编码和三路分类器自由引导丢弃的解耦交叉注意力机制注入扩散模型。与基线和三个消融变体的定量评估表明，所提出的架构实现了最高的水平线检测率0.850和最高的三分法对齐度0.817。类别特定的消融进一步表明，在组合同质场景子集上训练相比混合训练可将水平线偏差降低多达40%。这确立了组合控制精度是类别依赖的。
英文摘要：
Image generative models, though widely used as creative tools, offer limited support for the kind of compositional control that photographers and visual artists routinely exercise. This paper presents early results on an anchor conditioned finetuning framework for landscape image generation, in which a four dimensional compositional anchor vector is extracted from training images and injected into a diffusion model via a decoupled cross attention mechanism with Fourier encoding and three way classifier free guidance dropout. Quantitative evaluation against a baseline and three ablation variants shows that the proposed architecture achieves the highest horizon detection rate of 0.850 and the highest rule of thirds alignment of 0.817. A category specific ablation further demonstrates that training on compositionally homogeneous scene subsets reduces horizon deviation by up to 40 percent compared to mixed training. This establishes that compositional control precision is category dependent.
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。
