I work in the translation industry, and the interesting part of this to me is the implementation. Generating the resulting translation image in real time is a unique idea that is probably hard to make work well. OCR on a mobile device without a network connection is not as difficult as you might think (read: it can fairly easily be done on Android with tesseract-ocr, at least). Also, instead of the typical rule-based or statistical machine translation you get on the web, think of translating word-by-word as simply substituting words from a key/value dictionary list.

Having said that, I'm always glad to see interesting translation being developed and getting such a positive reaction on HN. Congratulations to Word Lens on launching!