We present X-MDPT (Cross-view Masked Diffusion Prediction Transformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes itself by employing masked diffusion transformers that operate on latent patches, a departure from the commonly-used Unet structures in existing works. The model comprises three key modules: 1) a denoising diffusion Transformer, 2) an aggregation network that consolidates conditions into a single vector for the diffusion process, and 3) a mask cross-prediction module that enhances representation learning with semantic information from the reference image. X-MDPT demonstrates scalability, improving FID, SSIM, and LPIPS with larger models. Despite its simple design, our model outperforms state-of-the-art approaches on the DeepFashion dataset while exhibiting efficiency in terms of training parameters, training time, and inference speed. Our compact 33MB model achieves an FID of 7.42, surpassing a prior Unet latent diffusion approach (FID 8.07) using only $11\times$ fewer parameters. Our best model surpasses the pixel-based diffusion with $\frac{2}{3}$ of the parameters and achieves $5.43 \times$ faster inference.

翻译：我们提出X-MDPT（跨视角掩码扩散预测变换器），一种用于姿态引导人体图像生成的新型扩散模型。X-MDPT的独特之处在于采用作用于潜在图块的掩码扩散变换器，这与现有工作中常用的Unet结构形成鲜明对比。该模型包含三个关键模块：1）去噪扩散变换器，2）将条件整合为单个向量用于扩散过程的聚合网络，以及3）通过参考图像语义信息增强表征学习的掩码交叉预测模块。X-MDPT展现出可扩展性，通过更大规模的模型在FID、SSIM和LPIPS指标上均有提升。尽管设计简洁，我们的模型在DeepFashion数据集上优于现有最先进方法，同时在训练参数、训练时间和推理速度方面展现出高效性。我们仅有33MB的紧凑模型取得了7.42的FID分数，仅用$\frac{1}{11}$的参数就超越了之前的Unet潜在扩散方法（FID 8.07）。我们的最佳模型以$\frac{2}{3}$的参数超越基于像素的扩散方法，并实现$5.43$倍的推理加速。