All Projects → EdVince → PSGAN-NCNN

EdVince / PSGAN-NCNN

Licence: other
PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡

Programming Languages

C++
36643 projects - #6 most used programming language
c
50402 projects - #5 most used programming language

Projects that are alternatives of or similar to PSGAN-NCNN

Ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+9454.29%)
Mutual labels:  ncnn, onnx
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Stars: ✭ 6,570 (+4592.86%)
Mutual labels:  ncnn, onnx
deepvac
PyTorch Project Specification.
Stars: ✭ 507 (+262.14%)
Mutual labels:  ncnn, onnx
Deepdetect
Deep Learning API and Server in C++14 support for Caffe, Caffe2, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
Stars: ✭ 2,306 (+1547.14%)
Mutual labels:  dlib, ncnn
Face-Recognition-Attendance-System
A simple python script that recognises faces and mark attendance for the recognised faces in an excel sheet.
Stars: ✭ 57 (-59.29%)
Mutual labels:  dlib
color-aware-style-transfer
Reference code for the paper CAMS: Color-Aware Multi-Style Transfer.
Stars: ✭ 36 (-74.29%)
Mutual labels:  style-transfer
Artistic-Style-Transfer-using-Keras-Tensorflow
Art to Image Style Transfer using Keras and Tensorflow.
Stars: ✭ 22 (-84.29%)
Mutual labels:  style-transfer
arcface retinaface mxnet2onnx
arcface and retinaface model convert mxnet to onnx.
Stars: ✭ 53 (-62.14%)
Mutual labels:  onnx
android tflite
GPU Accelerated TensorFlow Lite applications on Android NDK. Higher accuracy face detection, Age and gender estimation, Human pose estimation, Artistic style transfer
Stars: ✭ 105 (-25%)
Mutual labels:  style-transfer
mix-stage
Official Repository for the paper Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach published in ECCV 2020 (https://arxiv.org/abs/2007.12553)
Stars: ✭ 22 (-84.29%)
Mutual labels:  style-transfer
GLStyleNet
Semantic style transfer, code and data for "GLStyleNet: Exquisite Style Transfer Combining Global and Local Pyramid Features" (IET Computer Vision 2020)
Stars: ✭ 48 (-65.71%)
Mutual labels:  style-transfer
TitleStylist
Source code for our "TitleStylist" paper at ACL 2020
Stars: ✭ 72 (-48.57%)
Mutual labels:  style-transfer
dlib
Dynamic loading library for C/C++
Stars: ✭ 19 (-86.43%)
Mutual labels:  dlib
mediapipe plus
The purpose of this project is to apply mediapipe to more AI chips.
Stars: ✭ 38 (-72.86%)
Mutual labels:  onnx
Face-Recognition-Jetson-Nano
Recognize 2000+ faces on your Jetson Nano with database auto-fill and anti-spoofing
Stars: ✭ 63 (-55%)
Mutual labels:  ncnn
onnx learn
No description or website provided.
Stars: ✭ 74 (-47.14%)
Mutual labels:  onnx
Neural-Style-Transfer
Using CNN to achieve style transfer
Stars: ✭ 14 (-90%)
Mutual labels:  style-transfer
Android-Tensorflow-Style-Transfer
An Android app built with an artistic style transfer neural network
Stars: ✭ 31 (-77.86%)
Mutual labels:  style-transfer
ofxDlib
An openFrameworks wrapper for dlib. http://dlib.net/
Stars: ✭ 52 (-62.86%)
Mutual labels:  dlib
torch-model-compression
针对pytorch模型的自动化模型结构分析和修改工具集,包含自动分析模型结构的模型压缩算法库
Stars: ✭ 126 (-10%)
Mutual labels:  onnx

PSGAN-NCNN

What

  1. PSGAN是CVPR2020上的一个妆容迁移的工作,该工程的目的是将PSGAN移植至c++,并将所有模型使用ncnn进行推理
  2. 妆容迁移:有一张上了妆的人脸图像A,有一张没上妆的素颜人脸图像B,妆容迁移就是给B上A的妆容

Introduce

image image

  1. PSGAN提出的模型是2stage的,第一个stage计算两个特征值gamma和beta,第二个stage才计算迁移后的妆容,所以有两个模型
  2. 人脸的预处理,PSGAN的实现用了dlib的人脸检测和人脸68点关键点,还有一个pytorch的人脸属性分割模型
  3. 如代码所示,我除了dlib的方法外,我还收集了可以在ncnn上运行人脸检测和人脸关键点的模型对dlib进行了替换

Source Code

  1. opencv_dlib_ncnn_vs2019:opencv + dlib + ncnn的VS2019工程(最直接实现)
  2. opencv-mobile_ncnn_vs2019:opencv-mobile + ncnn的VS2019工程(最小依赖实现)
  3. opencv-mobile_ncnn_qt_vs2019:opencv-mobile + ncnn + qt界面的VS2019工程

Resource

  1. 带有qt gui的exe程序: 百度网盘(提取码:6666) image
  2. 知乎分析文章:https://zhuanlan.zhihu.com/p/426474467

Reference

  1. PSGAN: https://github.com/wtjiang98/PSGAN
  2. ncnn: https://github.com/Tencent/ncnn
  3. dlib: https://github.com/davisking/dlib
  4. opencv: https://github.com/opencv/opencv
  5. opencv-mobile: https://github.com/nihui/opencv-mobile
  6. LFFD-with-ncnn: https://github.com/SyGoing/LFFD-with-ncnn
  7. Peppa-Facial-Landmark-PyTorch: https://github.com/ainrichman/Peppa-Facial-Landmark-PyTorch
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].