Deep image prior 'learns' on just one image

Re:Deep image prior 'learns' on just one image by sanxiyn on Thursday November 30, 2017 @10:53PM (#15821784)

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.

[ Parent | on HN ]

Re:Deep image prior 'learns' on just one image by eanzenberg on Friday December 01, 2017 @12:34AM (#15822154)

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

[ Parent | on HN ]

Re:Deep image prior 'learns' on just one image by sanxiyn on Friday December 01, 2017 @12:43AM (#15822175)

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

[ Parent | on HN ]