用一个模型实现任意两域间的跨域翻译，只需少量配对数据。
Universal Multi-Domain Translation via Diffusion Routers
- 通过中央域路由，用统一扩散模型实现多域间任意翻译。
- 在三个大规模基准上超越现有方法，直接与间接翻译均最优。
- 适合需要灵活跨域生成的场景，如草图到分割图转换。
多域翻译（MDT）旨在学习多个领域间的翻译关系，但现有方法要么需要完全对齐的数据对，要么只能处理训练中见过的领域组合，实用性受限且无法覆盖大量跨域映射。本文提出通用多域翻译（UMDT），旨在仅使用K-1个以中央域为枢纽的配对数据集，即可实现任意两个域之间的翻译。为此，我们提出扩散路由（DR）框架：一个基于扩散的统一模型，通过源域和目标域标签条件化单一噪声预测器，建模所有中心域与非中心域间的翻译。通过中央域路由，实现非中心域间的间接翻译；同时引入新型可扩展学习策略，结合变分界目标与高效Tweedie精修过程，支持直接非中心域映射。在三个大规模通用多域翻译基准上的实验表明，DR在间接与直接翻译任务中均达到最先进性能，采样成本更低，并解锁了如草图↔分割图等新任务。结果证明，DR是可扩展、通用的多域翻译框架。
原文摘要 · Abstract (English)
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.
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。