mediapipe
Linux-Fake-Background-Webcam
Our great sponsors
mediapipe | Linux-Fake-Background-Webcam | |
---|---|---|
49 | 16 | |
25,405 | 1,563 | |
2.1% | - | |
9.9 | 5.7 | |
6 days ago | about 2 months ago | |
C++ | Python | |
Apache License 2.0 | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
mediapipe
-
Mediapipe openpose Controlnet model for SD
mediapipe/docs/solutions/pose.md at master · google/mediapipe · GitHub
-
MEDIAPIPE on-device diffusion plugins for conditioned text-to-image generation
Today, we announce MediaPipe diffusion plugins, which enable controllable text-to-image generation to be run on-device. Expanding upon our prior work on GPU inference for on-device large generative models, we introduce new low-cost solutions for controllable text-to-image generation that can be plugged into existing diffusion models and their Low-Rank Adaptation (LoRA) variants.
-
Running a TensorFlow object detector model and drawing boxes around objects at 60 FPS - all in React Native / JavaScript!
You can just grab the TFLite version! https://github.com/google/mediapipe/blob/master/docs/solutions/models.md
-
OpenAI came after our domain because we use GPT in it
I believe Google already released transformers under an apache 2 license with a patent grant:
https://github.com/google/mediapipe/blob/master/mediapipe/mo...
-
Open source Background Remover: Remove Background from images and video using AI
I was going to say that I like the MediaPipe Selfie Segmentation model for doing this sort of thing in a web page, but I've just noticed (when getting the GitHub link[1]) that Google have marked the code as legacy[2] ... no idea if the new solution is better/easier to use[3].
For what it's worth, my CodePen using the old model is here: https://codepen.io/kaliedarik/pen/PopBxBM
[1] - https://github.com/google/mediapipe/blob/master/docs/solutio...
[2] - "Attention: Thank you for your interest in MediaPipe Solutions. As of April 4, 2023, this solution was upgraded to a new MediaPipe Solution."
[3] - https://developers.google.com/mediapipe/solutions/vision/ima...
-
[P] Pattern recognition
I have used mediapipe very successfully in multiple projects and it's very easy to get running. You can choose from many different vision tasks including hand landmarks ( https://github.com/google/mediapipe/blob/master/docs/solutions/hands.md )
-
Getting face feature pose statistics
I found MediaPipe's Face Mesh and was impressed with how simple it was to get going, but it just gives you the landmark points and I've not gone any further yet.
-
New ControlNet Face Model
We've trained ControlNet on a subset of the LAION-Face dataset using modified output from MediaPipe's face mesh annotator to provide a new level of control when generating images of faces.
-
Trained an ML model using TensorFlow.js to classify American Sign Language (ASL) alphabets on browser. We are creating an open-source platform and would love to receive your feedback on our project.
Medipaipe library link: https://mediapipe.dev/
-
mediapipe VS daisykit - a user suggested alternative
2 projects | 24 Mar 2023
Linux-Fake-Background-Webcam
-
Fake Cam doesn't work
I'm trying to install Linux-Fake-Background-Webcam, which in turn requires 4l2loopback. Following the 4l2loopback manual, I try the following command to install it:
- Linux-Fake-Background-Webcam: Faking your webcam background under GNU/Linux.
- Best OS for Java dev
-
How Not to Support Desktop GNU+Linux, Zoom Edition
> Is this really a problem with Zoom or one with Wayland and the Linux distros?
I would say this is really a problem with Zoom, mostly due to the lack of attention paid to their web client.
For me, when it comes to video conferencing, the "table stakes" is working duplex audio over bluetooth, and so far only pipewire has solved this, which means Linux only.
After that, two very important features to have are screen sharing and background blur. For screen sharing, both Chrome/Chromium and Firefox have great support for screencast over pipewire, and so do many wayland compositors such as KDE kwin. As such, on a "pure" wayland system with no X11 window [1], screen sharing is also a solved problem.
Background blur is more ... complicated. When Google Meet rolled out https://ai.googleblog.com/2020/10/background-features-in-goo..., it immediately worked with chrome/chromium, on either wayland or X11. However, to this day, I think it still doesn't work with firefox, for whatever reason. Meanwhile, Zoom Linux client only started to support background blur (without green screen) since 5.7.6 released in August 2021, while Zoom web client remains hopeless.
In my previous job, we use Google Meet, and all is well with wayland. In the current one, we use Zoom, and I have to setup https://github.com/fangfufu/Linux-Fake-Background-Webcam as a workaround.
[1] This is very much doable these days, unless you want to run Slack desktop, which is hit-and-miss when running with --ozone-platform=wayland (unlike other electron-based apps such as Signal desktop), and of course the Zoom Linux app, which is just crap, as described in the article. Solution: run Slack and Zoom as Firefox tabs.
-
How Not to Support Desktop GNU+Linux, Zoom Edition (working Wayland support coming soon?)
I was going to say, Zoom's absolutely broken greenscreen support is nicely hacked in X by the community with this excellent repo: https://github.com/fangfufu/Linux-Fake-Background-Webcam
- Background Blur by video call on Teams Linux
-
Python Script Workaround to Be Able to Use Virtual Backgrounds in MS Teams for Linux
It seems pretty cool, but why does it need to be run as root? I can run Linux-Fake-Background-Webcam just fine without root!
-
Zoom gains virtual background without green screen functionality
I use https://github.com/fangfufu/Linux-Fake-Background-Webcam and it works great (realtime) for video background removal.
- How do I enable Zoom virtual background without green screen in Linux?
- I updated my Linux webcam background replacement tool to use Google's Mediapipe as image segmentation backend. It is now so much faster!
What are some alternatives?
openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
deepbacksub - Virtual Video Device for Background Replacement with Deep Semantic Segmentation
ue4-mediapipe-plugin - UE4 MediaPipe plugin
fake-chroma-key
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
Jitsi Meet - Jitsi Meet - Secure, Simple and Scalable Video Conferences that you use as a standalone app or embed in your web application.
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
virtual_webcam_background - Use a virtual webcam background and overlays with body-pix and v4l2loopback
BlazePose-tensorflow - A third-party Tensorflow Implementation for paper "BlazePose: On-device Real-time Body Pose tracking".
backgroundremover - Background Remover lets you Remove Background from images and video using AI with a simple command line interface that is free and open source.
jeelizFaceFilter - Javascript/WebGL lightweight face tracking library designed for augmented reality webcam filters. Features : multiple faces detection, rotation, mouth opening. Various integration examples are provided (Three.js, Babylon.js, FaceSwap, Canvas2D, CSS3D...).
webcam-virtual-background - Enjoying web conference with virtual backgrounds on linux