taylorlu

FaceBasisBuild

pixrefer-tf2

FaceFormer

[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers

DECA

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

voicepuppet

Audio driven video synthesis

torch-ngp

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

tiny-cuda-nn

Lightning fast C++/CUDA neural network framework

py360convert

Python implementation of convertion between equirectangular, cubemap and perspective. (equirect2cube, cube2equirect, equirect2perspec)

VIBE

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

Michelangelo

Speaker-Diarization

speaker diarization by uis-rnn and speaker embedding by vgg-speaker-recognition

dulcet

epitran

A tool for transcribing orthographic text as IPA (International Phonetic Alphabet)

TransformerTTS

🤖💬 Transformer TTS: Implementation of a non-autoregressive Transformer based neural network for text to speech.

ffmpeg-gl-transition

FFmpeg filter for applying GLSL transitions between video streams.

opencv-3.4.0

LSH modify

ocrlite

text detect and recognition on iOS platform

detectron2

CommonOCR

mesh

MPI-IS Mesh Processing Library

thomsonProblem

MachineLearningDOC

图像、人脸、OCR、语音相关算法整理

ocrDetect

ocr detect using psenet

FacePlayer

Face converter in video

TS2FLV

imgFinderServer

image retrieve based on lsh and akaze feature

attentionOCR

AudioKWS

Audio Keyword Search

donglu.github.io

ghostvlad-speaker

An tensorflow implementation of ghostvlad for speaker recognition