Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligned tuples or can only handle domain pairs seen in training, limiting their practicality and excluding many cross-domain mappings. We introduce universal MDT (UMDT), a generalization of MDT that seeks to translate between any pair of $K$ domains using only $K-1$ paired datasets with a central domain. To tackle this problem, we propose Diffusion Router (DR), a unified diffusion-based framework that models all central$\leftrightarrow$non-central translations with a single noise predictor conditioned on the source and target domain labels. DR enables indirect non-central translations by routing through the central domain. We further introduce a novel scalable learning strategy with a variational-bound objective and an efficient Tweedie refinement procedure to support direct non-central mappings. Through evaluation on three large-scale UMDT benchmarks, DR achieves state-of-the-art results for both indirect and direct translations, while lowering sampling cost and unlocking novel tasks such as sketch$\leftrightarrow$segmentation. These results establish DR as a scalable and versatile framework for universal translation across multiple domains.

翻译：多领域翻译（MDT）旨在学习多个领域之间的翻译，然而现有方法要么需要完全对齐的元组，要么只能处理训练中见过的领域对，这限制了其实用性并排除了许多跨领域映射。我们引入了通用多领域翻译（UMDT），这是MDT的一种推广，旨在仅使用$K-1$个与中心领域配对的数据集，实现任意$K$个领域之间的翻译。为解决此问题，我们提出了扩散路由器（DR），这是一个统一的基于扩散的框架，它通过一个以源领域和目标领域标签为条件的单一噪声预测器，建模所有中心$\leftrightarrow$非中心翻译。DR通过中心领域路由，实现了间接的非中心翻译。我们进一步引入了一种新颖的可扩展学习策略，该策略包含一个变分下界目标和一个高效的Tweedie细化过程，以支持直接的非中心映射。通过在三个大规模UMDT基准上的评估，DR在间接和直接翻译方面均取得了最先进的结果，同时降低了采样成本，并解锁了诸如草图$\leftrightarrow$分割等新任务。这些结果确立了DR作为一个可扩展且通用的框架，用于跨多个领域的通用翻译。