backscrub
backscrub copied to clipboard
floe
Virtual Video Device for Background Replacement with Deep Semantic Segmentation
More of a notes than an issue but at this point tensorflow does not compile with gcc 11, so if needed here are the notes on how to compile. Changes...
Hi, First thanks for all your work, After testing all the model given here i realize that none of then is really good for detecting hand. Do you know any...
While discussing some things about ANN with @martok it has been noted, that when experimenting with such networks they seem to be sensitive to noise in their inputs. As camera's...
_Originally posted by @phlash in https://github.com/floe/backscrub/issues/77#issuecomment-835513517_ > Sounds like a nice solution, but is the metadata normally included in models? Sounds like models with metadata should essentially be a zip...
Would be great to have your team test out DeepBackSub on Twitch, for many music artists looking for more tools for live streaming sets to their fans, and Twitch users...
The output shape in the model card is 265x256x2, however the model that we have here outputs 256x256x1. The model size also differs by a few KB.
I just found out about: https://elder.dev/posts/open-source-virtual-background/ But it's in python. Can someone make this work with deepbaksub? :)
Restarting the process could be inconvenient in some scenarios. The simplest way to do this would be to regularly check whether the background file has been replaced.
Calculating multiple slightly shifted segmentation masks would let us make a higher resolution combined mask. The segmentation input would be shifted by a few pixels up or down each time...
Allow for a second v4l2loopback cam output to be enabled which receives the image mask detected by the NN (plain mask, no source image). Depending on what is available this...