让AI生成图的透视更真实，用户可一键修正错误消失点。
ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points
- 通过建筑轮廓提取结构引导，修正图像中平行线的消失点偏差。
- 在保持原图视觉质量的同时，显著提升建筑场景的几何一致性。
- 适合需要精确空间结构的领域，如3D重建和虚拟场景设计。
近期的文本到图像模型（如Stable Diffusion）虽具备出色的视觉质量，但常因几何不一致而影响场景结构的真实感，尤其是消失点错位问题：平行线在二维空间中未能正确汇聚，导致空间结构失真，尤其在建筑类图像中更为明显。本文提出ControlVP，一种用户引导的框架，用于修复生成图像中的消失点不一致问题。该方法扩展了预训练扩散模型，引入由建筑轮廓提取的结构引导信号，并加入显式几何约束，强制图像边缘与透视线索对齐。实验表明，该方法在维持基线视觉保真度的同时，显著提升了全局几何一致性。该能力对需要精准空间结构的应用（如图像转3D重建）具有重要价值。代码与数据集已公开于https://github.com/RyotaOkumura/ControlVP。
原文摘要 · Abstract (English)
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 https://github.com/RyotaOkumura/ControlVP .
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。