Pinned Repositories
2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement
2019CCF-BDCI大赛 最佳创新探索奖获得者 基于OCR身份证要素提取赛题冠军 天晨破晓团队 赛题源码
2D_detection
TensorFlow implementation of SqueezeDet, trained on the KITTI dataset.
CodeFun
📚 这绝对是一份好看的深度学习笔记了😏
Dense-Head-Pose-Estimation
[ECCV 2020] Reimplementation of "Towards Fast, Accurate and Stable 3D Dense Face Alignment", face mesh, head pose, landmarks, and more.
drone_landing
SJTU Innovation Competition of AR.Drone
GrabCut_CUDA
GrabCut based video segmentation boosted with CUDA
GroupNorm-reproduce
A collection of code in different frameworks that reproduces experiments in "Group Normalization"
nnvm
Bring deep learning to bare metal
SCS-PRJ
基于caffe的视频监控系统
velo2cam_calibration
Automatic Calibration algorithm for Lidar-Stereo camera. ROS Package.
hajungong007's Repositories
hajungong007/aahq-dataset
Artstation-Artistic-face-HQ Dataset (AAHQ)
hajungong007/aistplusplus_api
API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset
hajungong007/April-Tag-VR-FullBody-Tracker
Full-body tracking in VR using AprilTag markers.
hajungong007/AR_100Days
hajungong007/AYolov2
hajungong007/bizarre-pose-estimator
WACV2022: Transfer Learning for Pose Estimation of Illustrated Characters
hajungong007/BlendShapeMaker
BlendShapeMaker python3.6
hajungong007/BlendyPose
Blender Motion Capture using your camera!
hajungong007/ClickSEG
hajungong007/Deep3DFaceRecon_pytorch
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.
hajungong007/Deep3DMM
Official repository for the CVPR 2021 paper "Learning Feature Aggregation for Deep 3D Morphable Models"
hajungong007/face_segmentation
Deep face segmentation in extremely hard conditions
hajungong007/FaceFormer
[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers
hajungong007/FACEGOOD-Audio2Face
http://www.facegood.cc
hajungong007/facemoji-kit
Face tracker with blend shapes coefficients, 3D head pose and dense mesh in real-time on iOS, Android, Mac, PC and Linux.
hajungong007/freemocap
Free Motion Capture for Everyone 💀✨
hajungong007/HRNet_cpp
HRNet的C++版本的推理实现
hajungong007/iCartoonFace
iCartoonFace dataset, and baseline approaches, the project is supported by iQIYI
hajungong007/light-face-detection
Light Face Detection using PyTorch Lightning
hajungong007/MeInGame
MeInGame: Create a Game Character Face from a Single Portrait, AAAI 2021
hajungong007/MocapNET
We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance
hajungong007/nlpcda
一键中文数据增强包 ； NLP数据增强、bert数据增强、EDA：pip install nlpcda
hajungong007/pose_demo_android
pose demo on android mobile based on PaddleDetection
hajungong007/SADRNet
[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
hajungong007/Silent-Face-Anti-Spoofing
静默活体检测（Silent-Face-Anti-Spoofing）
hajungong007/SimSwap
The official project of SimSwap (ACM MM 2020)
hajungong007/sofgan
[TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling
hajungong007/Tencent_Project
The invention relates to a method for cartoon face data synthesis.
hajungong007/VNN
VNN是由欢聚集团(Joyy Inc.)推出的高性能、轻量级神经网络部署框架。目前已为Hago、VOO、VFly、马克相机等App提供20余种AI能力的支持，覆盖直播、短视频、视频编辑等泛娱乐场景和工程场景
hajungong007/VOO
VOO是由欢聚集团(Joyy Inc.)推出的视频剪辑软件。不仅可以用于剪辑视频，还可以制作视频模板并分享发布出去。里面包括的视频，音频，贴纸，文字，特效，转场，AI高级特效，粒子特效等多种素材，还有属性关键帧，曲线变速，动画等功能。