Removing background and using larger image

I just found this repo after banging my head a few times in DeepLab and not getting any answers.
The post on Nvidia's website mentioned that the Semantic Segmentation can be used to remove background from a image with better accuracy (than the rest I assume) ?
https://news.developer.nvidia.com/this-ai-can-automatically-remove-the-background-from-a-photo/

Can we detect a person and remove the background (ultimately extracting the person only in a transparent png) ? If so, any pointers on how to achieve it ? Still learning.
Secondly, Can we use larger input images and get same size output images ? DeepLab and most of the models rescale input image to 512px and output same 512px/smaller images. I wanted to try doing this on 1k px or even larger images, and to get similar size/resolution output.

Again, sorry for asking noob questions, I am still trying this repo and learning.