BenBE

The new selfie model sure seems promising. What I think is still missing is the overlapping of masks to fill the whole image area from multiple NN runs.

Given we already have `cmake` in place this somewhat calls for `CTest` …

Maybe we should try to put our models as resources to `/usr/share/backscrub/models` following the FHS … People could still override that path by giving a full path name, but paths...

ACK, with the small note that this search apart from step 1 is only done for paths without a `/` in them.

For `htop` the `stderr` is completely redirected into a `memfd` and only ever dumped to the real `stderr` on abnormal exit. We may think about doing something similar here too....

Another idea for "automatic" tracking suggested by @martok the other day was recording some video of your background and automatically tagging everything above some noise threshold as foreground in order...

`v4l2loopback` is a kernel mode driver for Linux. No chance porting that driver to Windows. The part that may run on Windows is the actual image processing part inside `libbackscrub`,...

@phlash The core library part should mostly run on Windows as is (with maybe minor fixes). Where I currently see the biggest open questions is with the Camera Interface. Once...

Looking at your code changes this liiks like you are compiling with MSVC in pre-C++11 mode, as ```cpp #if !_WINDOWS return normalization_t{.scaling = 1/255.0, .offset = 0}; #else { normalization_t...

> One thing that confuses me is I don't understand the necessity of converting to and from YUV when displaying frames. The default pixel format for the virtual camera device...