Colour in Translation: Data, Models, and Benchmarking for Cross-Linguistic Colour Naming

Colour naming links vision and language. Yet, effective cross-linguistic colour communication is limited by the lack of systematic computational approaches for colour name translation. We collected 6,408 unique colour naming responses in five languages using online experiments and fieldwork. For each language, we trained a novel partially rotated decision trees model, to estimate colour naming distributions across the full gamut, consistently outperforming existing methods. Unlike prior work that assumed 11 universal colour categories, our results reveal cross-linguistic variation in naming granularity, with British English using 32 indispensable colour names, American English 47, French 27, Greek 32, and the Himba 7 to categorise the same perceptually uniform colour space. Building on these findings, we developed a translation benchmark that evaluates large language models on both lexical accuracy and perceptual colour differences. Our data, models, and benchmark provide an empirical foundation for inclusive design that reflects how people communicate colour across cultures.