Zoom , GoogleMeets에서 Vtuber 데뷔하기

Overview

EasyVtuber

  • Facial landmark와 GAN을 이용한 Character Face Generation
  • Google Meets, Zoom 등에서 자신만의 웹툰, 만화 캐릭터로 대화해보세요!
  • 악세사리는 어느정도 추가해도 잘 작동해요!
  • 안타깝게도 RTX 2070 미만에서는 실시간으로 잘 작동하지 않을 수도 있어요 ㅠㅠ



Demo



Requirements

  • Python >= 3.8
  • Pytorch >= 1.7
  • pyvirtualcam
  • mediapipe
  • opencv-python



Quick Start

  • ※ 이 프로젝트는 사용 전 OBS 설치가 필수입니다
  • 아래 설치 순서를 지켜주세요!
  1. OBS studio 설치

    • OBS virtualcam을 사용하기 위해서 먼저 OBS Studio를 설치해야합니다
  2. pip install -r requirements.txt

    • OBS virtualcam을 설치되어있어야 requirements에 포함된 pyvirtualcam이 정상적으로 설치되어 사용할 수 있습니다
  3. pretrianed model download

    • 아래 파일들을 pretrained folder에 넣어주세요
      • combiner.pt
      • eyebrow_decomposer.pt
      • eyebrow_morphing_combiner.pt
      • face_morpher.pt
      • two_algo_face_rotator.pt
  4. character image를 character folder에 넣어주세요

    • character image 파일은 다음의 조건을 충족해야합니다
      • alpha 채널을 포함할 것(png 확장자)
      • 1명의 인간형 캐릭터일 것
      • 캐릭터가 정면을 볼 것
      • 캐릭터의 머리가 128 x 128 pixel 내에 들어올 것 (기본적으로 256 x 256으로 resize되기 때문에 256 x 256 기준 128x128 안에 들어와야함)

    Example image is refenced by TalkingHeadAnime2

5.python main.py --webcam_output

  • 실제 facial feature가 어떻게 잡히는지 보고 싶다면 --debug 옵션을 추가하여 실행해주세요



How to make Custom Character

  1. 네이버, 구글 등에서 본인이 원하는 캐릭터를 찾으세요!
    • 되도록이면 위의 4가지 조건을 맞춰주세요! google search

  2. 찾은 이미지에서 캐릭터 얼굴이 중앙으로 가도록 가로세로 1:1 비율로 이미지를 잘라주세요!
  3. 이미지 배경을 제거해서 alpha 채널을 만들어 주세요!
  4. 완성!
    • character folder에 이미지를 넣고 python main.py --output_webcam --character (.png_제외한_캐릭터파일_이름) 실행!



Folder Structure

      │
      ├── character/ - character images 
      ├── pretrained/ - save pretrained models 
      ├── tha2/ - Talking Head Anime2 Library source files 
      ├── facial_points.py - facial feature point constants
      ├── main.py - main script to excute
      ├── models.py - GAN models defined
      ├── pose.py - process facial landmark to pose vector
      └── utils.py - util fuctions for pre/postprocessing image



Usage

webcam으로 송출 시

  • python main.py --output_webcam

캐릭터 지정

  • python main.py --character (character folder에 있는 .png를 제외한 캐릭터 파일 이름)

facial feature 확인 시

  • python main.py --debug

동영상 파일 inference

  • python main.py --input video파일_경로 --output_dir frame_저장할_디렉토리



TODOs

  • Add eyebrow feature
  • Parameter Controller GUI
  • Automation of Making Drivable Character



Thanks to



Acknowledgements

  • EasyVtuber는 TalkingHeadAnime2를 기반으로 제작되었습니다.
  • tha2 folder의 source와 pretrained model file은 원저작자 repo의 Liscense를 확인하고 사용하시기 바랍니다.
Owner
Gunwoo Han
EE student / Deep Learning / Computer Vision / Manager of 파이썬 처음처럼
Gunwoo Han
Awesome Spectral Indices in Python.

Awesome Spectral Indices in Python: Numpy | Pandas | GeoPandas | Xarray | Earth Engine | Planetary Computer | Dask GitHub: https://github.com/davemlz/

David Montero Loaiza 98 Jan 02, 2023
Deep LearningImage Captcha 2

滑动验证码深度学习识别 本项目使用深度学习 YOLOV3 模型来识别滑动验证码缺口,基于 https://github.com/eriklindernoren/PyTorch-YOLOv3 修改。 只需要几百张缺口标注图片即可训练出精度高的识别模型,识别效果样例: 克隆项目 运行命令: git cl

Python3WebSpider 117 Dec 28, 2022
PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

Description This is a PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector. Only RBOX part is implemented. Using dice loss

365 Dec 20, 2022
make a better chinese character recognition OCR than tesseract

deep ocr See README_en.md for English installation documentation. 只在ubuntu下面测试通过,需要virtualenv安装,安装路径可自行调整: git clone https://github.com/JinpengLI/deep

Jinpeng 1.5k Dec 28, 2022
Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)

Detecting Text in Natural Image with Connectionist Text Proposal Network The codes are used for implementing CTPN for scene text detection, described

Tian Zhi 1.3k Dec 22, 2022
FastOCR is a desktop application for OCR API.

FastOCR FastOCR is a desktop application for OCR API. Installation Arch Linux fastocr-git @ AUR Build from AUR or install with your favorite AUR helpe

Bruce Zhang 58 Jan 07, 2023
Read Japanese manga inside browser with selectable text.

mokuro Read Japanese manga with selectable text inside a browser. See demo: https://kha-white.github.io/manga-demo mokuro_demo.mp4 Demo contains excer

Maciej Budyś 170 Dec 27, 2022
A toolbox of scene text detection and recognition

FudanOCR This toolbox contains the implementations of the following papers: Scene Text Telescope: Text-Focused Scene Image Super-Resolution [Chen et a

FudanVIC Team 170 Dec 26, 2022
This repository lets you train neural networks models for performing end-to-end full-page handwriting recognition using the Apache MXNet deep learning frameworks on the IAM Dataset.

Handwritten Text Recognition (OCR) with MXNet Gluon These notebooks have been created by Jonathan Chung, as part of his internship as Applied Scientis

Amazon Web Services - Labs 422 Jan 03, 2023
Generic framework for historical document processing

dhSegment dhSegment is a tool for Historical Document Processing. Its generic approach allows to segment regions and extract content from different ty

Digital Humanities Laboratory 343 Dec 24, 2022
A small C++ implementation of LSTM networks, focused on OCR.

clstm CLSTM is an implementation of the LSTM recurrent neural network model in C++, using the Eigen library for numerical computations. Status and sco

Tom 794 Dec 30, 2022
Text to QR-CODE

QR CODE GENERATO USING PYTHON Author : RAFIK BOUDALIA. Installation Use the package manager pip to install foobar. pip install pyqrcode Usage from tki

Rafik Boudalia 2 Oct 13, 2021
Use Convolutional Recurrent Neural Network to recognize the Handwritten line text image without pre segmentation into words or characters. Use CTC loss Function to train.

Handwritten Line Text Recognition using Deep Learning with Tensorflow Description Use Convolutional Recurrent Neural Network to recognize the Handwrit

sushant097 224 Jan 07, 2023
A collection of resources (including the papers and datasets) of OCR (Optical Character Recognition).

OCR Resources This repository contains a collection of resources (including the papers and datasets) of OCR (Optical Character Recognition). Contents

Zuming Huang 363 Jan 03, 2023
A list of hyperspectral image super-solution resources collected by Junjun Jiang

A list of hyperspectral image super-resolution resources collected by Junjun Jiang. If you find that important resources are not included, please feel free to contact me.

Junjun Jiang 301 Jan 05, 2023
Random maze generator and solver

Maze Generator and Solver I wrote a maze generator that works with two commonly known algorithms: Depth First Search and Randomized Prims. Both of the

Daniel Pérez 10 Sep 23, 2022
scene-linear test images

Scene-Referred Image Collection A collection of OpenEXR Scene-Referred images, encoded as max 2048px width, DWAA 80 compression. All exrs are encoded

Gralk Klorggson 7 Aug 25, 2022
Pytorch implementation of PSEnet with Pyramid Attention Network as feature extractor

Scene Text-Spotting based on PSEnet+CRNN Pytorch implementation of an end to end Text-Spotter with a PSEnet text detector and CRNN text recognizer. We

azhar shaikh 62 Oct 10, 2022
A python program to block out your face

Readme This is a small program I threw together in about 6 hours to block out your face. It probably doesn't work very well, so be warned. By default,

1 Oct 17, 2021
SemTorch

SemTorch This repository contains different deep learning architectures definitions that can be applied to image segmentation. All the architectures a

David Lacalle Castillo 154 Dec 07, 2022