While perspective is a well-studied topic in art, it is generally taken for granted in images. However, for the recent wave of high-quality image synthesis methods such as latent diffusion models, perspective accuracy is not an explicit requirement. Since these methods are capable of outputting a wide gamut of possible images, it is difficult for these synthesized images to adhere to the principles of linear perspective. We introduce a novel geometric constraint in the training process of generative models to enforce perspective accuracy. We show that outputs of models trained with this constraint both appear more realistic and improve performance of downstream models trained on generated images. Subjective human trials show that images generated with latent diffusion models trained with our constraint are preferred over images from the Stable Diffusion V2 model 70% of the time. SOTA monocular depth estimation models such as DPT and PixelFormer, fine-tuned on our images, outperform the original models trained on real images by up to 7.03% in RMSE and 19.3% in SqRel on the KITTI test set for zero-shot transfer.

通过引入新的几何约束条件在生成模型的训练过程中强制进行透视准确性的要求，我们展示了使用该约束条件训练的生成模型的输出既更加逼真，同时还提高了在生成图像上进行训练的下游模型的性能。主观人类实验表明，使用我们约束条件训练的潜在扩散模型生成的图像在70%的情况下优于 Stable Diffusion V2 模型生成的图像。我们的图像微调后的 SOTA 单眼深度估计模型如 DPT 和 PixelFormer 在 KITTI 测试集上的零-shot 转移中 RMSE 上超过真实图像训练的原始模型最多 7.03%，SqRel 上超过 19.3%。

增强扩散模型与3D透视几何约束