Observation model is trivial and data-free. For example, just mean squared error... | Hacker News

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

		sanxiyn on Dec 1, 2017 \| parent \| context \| favorite \| on: Deep image prior 'learns' on just one image Observation model is trivial and data-free. For example, just mean squared error for denoising, mean squared error of downscaled image for super-resolution, etc.

eanzenberg on Dec 1, 2017 [–]

I'm fairly certain that's not? Where in the paper does it talk about this other network, generally called the discriminator?

sanxiyn on Dec 1, 2017 | [–]

There is no discriminator in this work. Read the paper.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact