virtual_webcam_background

virtual_webcam_background copied to clipboard

Implement a filter to translate the image to the detected head or eyes

5

I just wanted to play around with a mainly transparent image just containing some text which floats next to my head. It seems to work and does what I intended...

schuellerf

Main loop profiling and disabling unnecessary parts

1

This is not to be merged. Only contains suggestions on what parts are not always required to be calculated and should be skipped if applicable to gain more FPS. The...

janci007

error when trying to run the script

15

I get this error when trying to run `python ./virtual_webcam.py` ``` No module named 'numpy.core._multiarray_umath' ``` more specifically ``` ❯ python ./virtual_webcam.py 2022-12-12 11:14:30.381112: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is...

AntouanK

- Try out other segmentation networks (see e.g. https://huggingface.co/tasks/image-segmentation) - Refactor the script to better separate parts that need additional features from resnet/mobilnet and parts that only need the segmentation...

allo-

Unavailable in Zoom login screen, altough works in the real meeting

5

It works perfectly if I see the webcam with ``` mplayer tv://device=/dev/video0 ``` But it doesn't work with Zoom web interface, it says "Video unavailable at this time"  I...

raffaem

Document mediapipe

1

I think that `README.md` lacks the fact that the software supports mediapipe. It's the best filter for me.

raffaem

[question] Running on low resource devices

2

Hi, I don't have time to do a proper pull request, but I've written a detailed [blog post](https://kirk86.github.io/2022/02/virtual-webcam-background/) to run this project on intel-based macbook pro 2015. I was wondering...

kirk86

Video lagging while running

8

I've noticed that the video is quite lagging in real time introducing quite some latency making the the overall experience to the other users watching your video quite unpleasant. Even...

kirk86

possible synergies with backscrub

1

Hi just a heads up for a similar project (https://github.com/floe/backscrub) which has implemented the Google Meet Segmentation Model for tensorflow - I can actually achieve 25+ Frames on a normal...

coro1404

Using video filter results in ZeroDivisionError

5

Using the `video` filter with the following config item: ``` - "empty": [["video", "tumbleweed.gif", 5]] ``` I get the following error trace : ``` Loading video: tumbleweed.gif [ERROR:0] global /tmp/scratch/3942/pip-install-5mr76rqs/opencv-python_bb4cd8da7f5644bc83c7d0718e3f53ca/opencv/modules/videoio/src/cap.cpp...

faxm0dem