We introduce a general framework for generating diverse visual content, including ambiguous images, panorama images, mesh textures, and Gaussian splat textures, by synchronizing multiple diffusion processes. We present exhaustive investigation into all possible scenarios for synchronizing multiple diffusion processes through a canonical space and analyze their characteristics across applications. In doing so, we reveal a previously unexplored case: averaging the outputs of Tweedie's formula while conducting denoising in multiple instance spaces. This case also provides the best quality with the widest applicability to downstream tasks. We name this case SyncTweedies. In our experiments generating visual content aforementioned, we demonstrate the superior quality of generation by SyncTweedies compared to other synchronization methods, optimization-based and iterative-update-based methods.

通过同步多个扩散过程，我们引入了一个生成多样化视觉内容（包括模糊图像、全景图像、网格纹理和高斯斑点纹理）的通用框架，并通过一个标准空间对同步多个扩散过程的所有可能情况进行了详尽研究，并分析了它们在各种应用中的特点。在此过程中，我们揭示了一个以往未曾探索的情况：在多实例空间中进行去噪并对 Tweedie's 公式的输出取平均。这种情况提供了与下游任务的最广泛适用性相比最好的质量。我们将这种情况命名为 SyncTweedies。在我们生成上述视觉内容的实验中，我们证明了 SyncTweedies 相对于其他同步方法（基于优化和基于迭代更新的方法）的生成质量更高。

SyncTweedies: 基于同步扩散的通用生成框架