I don't quite see how this would help OCR at all? or am I misunderstanding what ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		aDyslecticCrow 3 months ago \| parent \| context \| favorite \| on: Meta Segment Anything Model 3 I don't quite see how this would help OCR at all? or am I misunderstanding what kind of OCR you're thinking of?

iandanforth 3 months ago [–]

Deepseek-OCR uses SAM V1 as a component in its pipeline already. It also does layout detection.

aDyslecticCrow 3 months ago | [–]

That sounds like ludicrous overkill to me.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact