Name: Yuki-Chai
Type: User
Company: Zhejiang University
Bio: Ph.D in Computer Science graduated from Zhejiang University, China. Speech-driven facial animation.
3D facial reconstruction (3DMM).
Location: Hangzhou, Zhejiang, China
Yuki-Chai's Projects
A python crawler for 1024 jap video from a mystery website. (No url)
Active Appearance Model
A jQuery plugin that simulates asynchronous file uploads.
http://nlp.seas.harvard.edu/2018/04/03/attention.html
Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose"
AudioDVP:Photorealistic Audio-driven Video Portraits
A collection of shaders to draw color maps.
Configuration system geared towards Python ML projects
Types and functions that make it a little easier to work with Core ML in Swift.
This mathematics course is taught for the first year Ph.D. students of computer science and related areas @ZJU
A date and time library based on the C++11/14/17 <chrono> header
The pytorch implementation of DC-TTS
DECA: Detailed Expression Capture and Animation
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
Speech Recognition using DeepSpeech2.
An implementation of Deformation Transfer algorithm in ANSI C
This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.
ffmpeg - Frame Accurate Seeking Extension - A library to accomplish frame-accurate seeking, and frame-counting, for video processing applications
RVL lossless depth image compression plugin for ffmpeg
An FFmpeg based source library and Avisynth/VapourSynth plugin for easy frame accurate access
A CMake version of https://github.com/FFMS/ffms2
Python I/O for optical flow files (.flo)