This repository is the zoo of image processing webworkers for javascript. You can use these workers as npm package.
Note. some module is not provided as webworker for safari because of it's restriction.
Webworkers
-
Webworkers
- bodypix
- facemesh
- asciiart
- opencv
- PoseNet
- HandPose
- White-Box-Cartoon
- BiseNetv2 Celeb A Mask
- U^2-Net Portrait Drawing
- MODNet
- Google meet person segmentation
- Multi Barcode Scanner
- Super Resolution
- Blazeface
- MediaPipe Hands
- MediaPipe Face landmark detection
- MediaPipe BlazePose
- MediaPipe Mix
- MediaPipe Mix2
- TFLite Wasm
- Libs
- Experiments
- Reference
bodypix
installation and usage
demo
facemesh
out2.mp4
installation and usage
demo
asciiart
installation and usage
demo
opencv
installation and usage
demo
PoseNet
installation and usage
demo
HandPose
installation and usage
demo
White-Box-Cartoon
installation and usage
demo
Note: very heavy process. It will take 40second or more to process one frame. be patient... demo demo(slow)
License
White-box CartoonGAN
Copyright (C) Xinrui Wang All rights reserved. Licensed under the CC BY-NC-SA 4.0
license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
Commercial application is prohibited, please remain this license if you clone this repo
Citation
BiseNetv2 Celeb A Mask
installation and usage
demo
reference
U^2-Net Portrait Drawing
installation and usage
demo
MODNet
installation and usage
demo
Note: Very heavy processing to open.
Licnece
This project (code, pre-trained models, demos, etc.) is released under the Creative Commons Attribution NonCommercial ShareAlike 4.0 license.
NOTE: The license will be changed to allow commercial use after this work is accepted by a conference or a journal.
Google meet person segmentation
installation and usage
demo
all all(slow) 96x160 96x160(slow) 128x128 128x128(slow) 144x256 144x256(slow) 256x256 256x256(slow)
Multi Barcode Scanner
installation and usage
demo
demo(movie)
-
Pixel3 https://youtu.be/IrPLMUuWaJk
-
Pixel4 https://youtu.be/Xxz1hFUAnKk
Licnece
This project (code, pre-trained models, demos, etc.) is released under the Creative Commons Attribution NonCommercial ShareAlike 4.0 license.
Super Resolution
installation and usage
demo
Blazeface
installation and usage
demo
MediaPipe Hands
installation and usage
demo
all all(slow) lite lite(slow) full full(slow) mediapipe mediapipe(slow) tfjs tfjs(slow)
MediaPipe Face landmark detection
installation and usage
demo
all all(slow) short short(slow) short_with_attention short_with_attention(slow) full full(slow) full_with_attention full_with_attention(slow) mediapipe mediapipe(slow) tfjs tfjs(slow)
MediaPipe BlazePose
installation and usage
demo
all all(slow) lite lite(slow) full full(slow) heavy heavy(slow) mediapipe mediapipe(slow) tfjs tfjs(slow)
MediaPipe Mix
Compose Mediapipe models(hand, face, pose). This module bundles whole models in one file. If you want to split them, use MediaPipe Mix2.
installation and usage
demo
MediaPipe Mix2
Compose Mediapipe models(hand, face, pose) version2. This module load models from external path. This requires some of skills. If you want to use simply, use MediaPipe Mix.
installation and usage
demo
TFLite Wasm
Google meet person segmentation(TFLite wasm)
demo
Added Selfie Segmentationmodelcard
White-Box-Cartoon(TFLite wasm)
demo
License
White-box CartoonGAN
Copyright (C) Xinrui Wang All rights reserved. Licensed under the CC BY-NC-SA 4.0
license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
Commercial application is prohibited, please remain this license if you clone this repo
ESPCN (TFLite wasm)
demo
https://flect-lab-web.s3-us-west-2.amazonaws.com/P01_wokers/tfl004_super_resolution/index.html
Libs
FaceSwap
Faceswap by using facemesh worker
demo
https://flect-lab-web.s3-us-west-2.amazonaws.com/P01_wokers/lib001_faceswap/index.html
Experiments
Exp.1 Multi-version based tfjs model
With webworker, we can use models which based on the differenct tfjs models.
demo
src
Citation
Exp.2 Performance improvement
With webworker, we can improve performance when we use multiple models.
demo
src
Citation
- Same as Exp.1
Reference
This repository was inspired by this site.
https://github.com/terryky/tfjs_webgl_app
Demo images are from pakutaso