Existing work has observed that current text-to-image systems do not
accurately reflect explicit spatial relations between objects such as 'left of'
or 'below'. We hypothesize that this is because explicit spatial relations
rarely appear in the image captions used to train these models. We propose an
automatic method that, given existing images, generates synthetic captions that
contain 14 explicit spatial relations. We introduce the Spatial Relation for
Generation (SR4G) dataset, which contains 9.9 millions image-caption pairs for
training, and more than 60 thousand captions for evaluation. In order to test
generalization we also provide an 'unseen' split, where the set of objects in
the train and test captions are disjoint. SR4G is the first dataset that can be
used to spatially fine-tune text-to-image systems. We show that fine-tuning two
different Stable Diffusion models (denoted as SD$_{SR4G}$) yields up to 9
points improvements in the VISOR metric. The improvement holds in the 'unseen'
split, showing that SD$_{SR4G}$ is able to generalize to unseen objects.
SD$_{SR4G}$ improves the state-of-the-art with fewer parameters, and avoids
complex architectures. Our analysis shows that improvement is consistent for
all relations. The dataset and the code will be publicly available.

现有文献观察到当前的文本到图像系统不能准确反映物体之间的显式空间关系，我们假设这是因为训练这些模型的图像标题很少包含显式空间关系。为此，我们提出了一种自动方法，给定现有图像生成包含 14 种显式空间关系的合成标题。我们引入了 Spatial Relation for Generation (SR4G) 数据集，其中包含 990 万个图像标题对进行训练，并且包含超过 6 万个用于评估的标题。为了测试泛化性能，我们还提供了一个 ' 未见过 ' 的分割，其中训练和测试标题中的对象集是不相交的。SR4G 是首个可以用于空间微调文本到图像系统的数据集。我们显示微调两个不同的稳定扩散模型（称为 SD$_{SR4G}$）可以使 VISOR 指标提升高达 9 个点。改进结果在 ' 未见过 ' 的分割中依然有效，表明 SD$_{SR4G}$ 可以推广到未见过的对象。SD$_{SR4G}$ 通过更少的参数改进了最先进的方法，并避免了复杂的架构。我们的分析显示改进对于所有关系都是一致的。数据集和代码将公开提供。