xueyedamo521's repositories
6DRepNet
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.
TinyNeuralNetwork
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
Gaze-Tracker
Building light weight eye trackers for mobile devices using simple Convolutional Neural Networks. This repo contains the work done during GSoC-2022 under @INCF.
OnePass-ASD
active speaker detection
FSDNet_RealTimeArch
Real-time Architecture for Audio-Visual Active Speaker Detection
FFR-Net
PyTorch code for ICIP 2022 paper "A Unified Framework for Masked and Mask-Free Face Recognition via Feature Rectification"
movenet.pytorch
A Pytorch implementation of MoveNet from Google. Include training code and pre-trained model.
JointBoneLoss
This is an implementation of Joint Bone Loss by myself. I try it on my own pose estimation task and achieve good performance. So I share with you guys, enjoy~
EyeMU
Gaze + IMU Gestures on Mobile Devices
kornia
Open Source Differentiable Computer Vision Library
torchlm
💎A high level pipeline for face landmarks detection, supports training, evaluating, exporting, inference and 100+ data augmentations, compatible with torchvision and albumentations, can easily install with pip.
movenet
Un-official implementation of MoveNet from Google
handpose_x
手部21个关键点检测,二维手势姿态,手势识别,pytorch,handpose
RobustVideoMatting-1
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
PoseEstimationForMobile
:dancer: Real-time single person pose estimation for Android and iOS.
3DMM-Fitting-Pytorch
A 3DMM fitting framework using Pytorch.
TCVOM
Github project for Attention-guided Temporal Coherent Video Object Matting.
AIM
[IJCAI'21] Deep Automatic Natural Image Matting
onnx-tensorflow
Tensorflow Backend for ONNX
opencv-mobile
The minimal opencv for Android, iOS and ARM Linux
CainCamera
CainCamera is an Android Project to learn about development of beauty camera, image and short video
MERL-RAV_dataset
MERL-RAV Dataset (CVPR 2020) contains over 19k faces annotated with 68 landmarks, with the additional information of whether each landmark is unoccluded, self-occluded or externally occluded.
MODNet
A Trimap-Free Solution for Portrait Matting in Real Time under Changing Scenes
Dense-Head-Pose-Estimation
[ECCV 2020] Reimplementation of 3DDFAv2, including face mesh, head pose, landmarks, and more.
BackgroundMattingV2-TensorFlow
TensorFlow implementation of Real-Time High-Resolution Background Matting
ContactHands
Detecting Hands and Recognizing Physical Contact in the Wild, NeurIPS 2020.
EgoDaily
EgoDaily database