Hacker News Reader

Parent Full thread

stared

I think we are on the first steps of a very interesting road related to using DL for image processing:

- Automatically cutting a person or an object https://www.remove.bg/

- Turning 2d photos in 3d perspective videos https://shihmengli.github.io/3D-Photo-Inpainting/

- Artistic style transfer for videos https://www.youtube.com/watch?v=Khuj4ASldmU

- Super-resolution for old games https://www.resetera.com/threads/ai-neural-networks-being-us...

Etc, etc.

View on HN

There are lots of great image processing algorithms also outside of DL. Search for "Siggraph" on youtube. If only these algorithms were easily accessible as plugins in GIMP ...

https://en.wikipedia.org/wiki/SIGGRAPH

Unfortunately writing a paper about implementing your new fancy algorithm (TM) in GIMP is hardly ever successful, so many of those die in some git repo.

I assume (hope) it won’t be long before erasing objects within a scene and adding new ones (e.g. clouds) are widespread, too.

Reply on news.ycombinator.com