Abstract
Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural realism of generated scenes. One prominent issue is vanishing point inconsistency, where projections of parallel lines fail to converge correctly in 2D space. This leads to structurally implausible geometry that degrades spatial realism, especially in architectural scenes. We propose ControlVP, a user-guided framework for correcting vanishing point inconsistencies in generated images. Our approach extends a pre-trained diffusion model by incorporating structural guidance derived from building contours. We also introduce geometric constraints that explicitly encourage alignment between image edges and perspective cues. Our method enhances global geometric consistency while maintaining visual fidelity comparable to the baselines. This capability is particularly valuable for applications that require accurate spatial structure, such as image-to-3D reconstruction. The dataset and source code are available at this https URL .
Abstract (translated)
最近的文本到图像生成模型，如Stable Diffusion，在视觉质量方面取得了显著成就，但这些模型常常存在几何不一致性的问题，这会损害生成场景的结构真实感。其中一个突出问题是消失点不一致，即平行线在二维空间中的投影未能正确汇聚。这种情况会导致结构上不合理且破坏了空间的真实感，尤其是在建筑场景中更为明显。 为了解决这些问题，我们提出了ControlVP，这是一种用户引导框架，用于纠正生成图像中的消失点不一致性。我们的方法通过将从建筑物轮廓导出的结构指导信息加入到预训练的扩散模型中来扩展该模型。此外，我们引入了几何约束条件，以明确地促进图像边缘与透视线索之间的对齐。 这种方法在保持视觉保真度与基线水平相当的同时增强了全局几何一致性。这种能力对于需要准确空间结构的应用特别有价值，例如从图像到3D重建的应用。数据集和源代码可在该链接中获取：[此URL]（请将“this https URL”替换为实际提供的链接）。
URL
https://arxiv.org/abs/2512.07504
