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
TableBank: A Benchmark Dataset for Table Detection and Recognition

TableBank TableBank is a new image-based table detection and recognition dataset built with novel weak supervision from Word and Latex documents on th

844 Jan 04, 2023
Handwritten_Text_Recognition

Deep Learning framework for Line-level Handwritten Text Recognition Short presentation of our project Introduction Installation 2.a Install conda envi

24 Jul 15, 2022
Demo for the paper "Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation"

Streaming speaker diarization Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation by Juan Manuel Coria, Hervé

Juanma Coria 185 Jan 01, 2023
Text recognition (optical character recognition) with deep learning methods.

What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis | paper | training and evaluation data | failure cases and cle

Clova AI Research 3.2k Jan 04, 2023
Sign Language Recognition service utilizing a deep learning model with Long Short-Term Memory to perform sign language recognition.

Sign Language Recognition Service This is a Sign Language Recognition service utilizing a deep learning model with Long Short-Term Memory to perform s

Martin Lønne 1 Jan 08, 2022
OpenCVを用いたカメラキャリブレーションのサンプルです。2021/06/21時点でPython実装のある3種類(通常カメラ向け、魚眼レンズ向け(fisheyeモジュール)、全方位カメラ向け(omnidirモジュール))について用意しています。

OpenCV-CameraCalibration-Example FishEyeCameraCalibration.mp4 OpenCVを用いたカメラキャリブレーションのサンプルです 2021/06/21時点でPython実装のある以下3種類について用意しています。 通常カメラ向け 魚眼レンズ向け(

KazuhitoTakahashi 34 Nov 17, 2022
Image processing in Python

scikit-image: Image processing in Python Website (including documentation): https://scikit-image.org/ Mailing list: https://mail.python.org/mailman3/l

Image Processing Toolbox for SciPy 5.2k Dec 30, 2022
Shape Detection - It's a shape detection project with OpenCV and Python.

Shape Detection It's a shape detection project with OpenCV and Python. Setup pip install opencv-python for doing AI things. pip install simpleaudio fo

1 Nov 26, 2022
TextBoxes re-implement using tensorflow

TextBoxes-TensorFlow TextBoxes re-implementation using tensorflow. This project is greatly inspired by slim project And many functions are modified ba

Gu Xiaodong 44 Dec 29, 2022
Automatically remove the mosaics in images and videos, or add mosaics to them.

Automatically remove the mosaics in images and videos, or add mosaics to them.

Hypo 1.4k Dec 30, 2022
Implement 'Single Shot Text Detector with Regional Attention, ICCV 2017 Spotlight'

SSTDNet Implement 'Single Shot Text Detector with Regional Attention, ICCV 2017 Spotlight' using pytorch. This code is work for general object detecti

HotaekHan 84 Jan 05, 2022
かの有名なあの東方二次創作ソング、「bad apple!」のMVをPythonでやってみたって話

bad apple!! 内容 このプログラムは、bad apple!(feat. nomico)のPVをPythonを用いて再現しよう!という内容です。 実はYoutube並びにGithub上に似たようなプログラムがあったしなんならそっちの方が結構良かったりするんですが、一応公開しますw 使い方 こ

赤紫 8 Jan 05, 2023
Text-to-Image generation

Generate vivid Images for Any (Chinese) text CogView is a pretrained (4B-param) transformer for text-to-image generation in general domain. Read our p

THUDM 1.3k Jan 05, 2023
A real-time dolly zoom camera effect

Dolly-Zoom I've always been amazed by the gradual perspective change of dolly zoom, and I have some experience in python and OpenCV, so I decided to c

Dylan Kai Lau 52 Dec 08, 2022
Code release for our paper, "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo"

SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo Thomas Kollar, Michael Laskey, Kevin Stone, Brijen Thananjeyan

68 Dec 14, 2022
Code for CVPR2021 paper "Learning Salient Boundary Feature for Anchor-free Temporal Action Localization"

AFSD: Learning Salient Boundary Feature for Anchor-free Temporal Action Localization This is an official implementation in PyTorch of AFSD. Our paper

Tencent YouTu Research 146 Dec 24, 2022
Rubik's Cube in pygame with OpenGL

Rubik Rubik's Cube in pygame with OpenGL The script show on the screen a Rubik Cube buit with OpenGL. Then I have also implemented all the possible mo

Gabro 2 Apr 15, 2022
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
Give a solution to recognize MaoYan font.

猫眼字体识别 该 github repo 在于帮助xjtlu的同学们识别猫眼的扭曲字体。已经打包上传至 pypi ,可以使用 pip 直接安装。 猫眼字体的识别不出来的原理与解决思路在采茶上 使用方法: import MaoYanFontRecognize

Aruix 4 Jun 30, 2022