All Projects → EdVince → ClothingTransfer-NCNN

EdVince / ClothingTransfer-NCNN

Licence: other
CT-Net, OpenPose, LIP_JPPNet, DensePose running with ncnn⚡服装迁移/虚拟试穿⚡ClothingTransfer/Virtual-Try-On⚡

Programming Languages

C++
36643 projects - #6 most used programming language
c
50402 projects - #5 most used programming language
CMake
9771 projects

Projects that are alternatives of or similar to ClothingTransfer-NCNN

EverybodyDanceNow reproduce pytorch
Everybody dance now reproduced in pytorch
Stars: ✭ 579 (+248.8%)
Mutual labels:  openpose
FastPose
pytorch realtime multi person keypoint estimation
Stars: ✭ 36 (-78.31%)
Mutual labels:  openpose
MaixPy3
MaixPy for Linux Python3, let's play with edge AI easier!
Stars: ✭ 125 (-24.7%)
Mutual labels:  ncnn
Face-Recognition-Jetson-Nano
Recognize 2000+ faces on your Jetson Nano with database auto-fill and anti-spoofing
Stars: ✭ 63 (-62.05%)
Mutual labels:  ncnn
posture recognition
Posture recognition based on common camera
Stars: ✭ 91 (-45.18%)
Mutual labels:  openpose
Jetson-Nano-image
Jetson Nano image with deep learning frameworks
Stars: ✭ 46 (-72.29%)
Mutual labels:  ncnn
ncnn-android-benchmark
ncnn android benchmark app
Stars: ✭ 78 (-53.01%)
Mutual labels:  ncnn
openpose-docker
A docker build file for CMU openpose with Python API support
Stars: ✭ 68 (-59.04%)
Mutual labels:  openpose
OpenPoseDotNet
OpenPose wrapper written in C++ and C# for Windows
Stars: ✭ 55 (-66.87%)
Mutual labels:  openpose
YOLOv5-Lite
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
Stars: ✭ 1,230 (+640.96%)
Mutual labels:  ncnn
ncnn-yolov4-int8
NCNN+Int8+YOLOv4 quantitative modeling and real-time inference
Stars: ✭ 20 (-87.95%)
Mutual labels:  ncnn
PSGAN-NCNN
PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡
Stars: ✭ 140 (-15.66%)
Mutual labels:  ncnn
denseposeInstalltion
How to Install DensePose
Stars: ✭ 20 (-87.95%)
Mutual labels:  densepose
ESP32-CAM-MJPEG-Stream-Decoder-and-Control-Library
The library is MJPEG stream decoder based on libcurl and OpenCV, and written in C/C++.
Stars: ✭ 40 (-75.9%)
Mutual labels:  openpose
ffcnn
ffcnn is a cnn neural network inference framework, written in 600 lines C language.
Stars: ✭ 50 (-69.88%)
Mutual labels:  ncnn
deepvac
PyTorch Project Specification.
Stars: ✭ 507 (+205.42%)
Mutual labels:  ncnn
libdeepvac
Use PyTorch model in C++ project
Stars: ✭ 98 (-40.96%)
Mutual labels:  ncnn
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 (+3857.83%)
Mutual labels:  ncnn
daisykit
Daisykit is an easy AI toolkit for software engineers to integrate pretrained AI models and pipelines into their projects. - with NCNN, OpenCV, Python wrappers
Stars: ✭ 22 (-86.75%)
Mutual labels:  ncnn
RobotVision2
移动端实时疲劳驾驶检测
Stars: ✭ 23 (-86.14%)
Mutual labels:  ncnn

ClothingMigration-NCNN

What

  1. CT-Net:CVPR2021上的一个虚拟试穿/服装迁移的工作,该工程就是将CT-Net及其相关依赖网络移植到ncnn
  2. 服装迁移:给定一个人的图A,与另一个人的图B,将A的衣服穿到B的身上

PS

这个工作其实我个人计划做的一个系列,分三步:

  1. 仿妆 —— 已完成
  2. 换衣服 —— 已完成,就是该工程
  3. 换发型 —— 计划中

Introduce

这个没啥好说,看图就完事了,先看换男装的: image 再看女装: image 程序流程分析,假定目标服装图A,目标穿衣人B:

  1. 对A与B都应用OpenPose得到candidate和subset
  2. 对A与B都应用JIP_LPPNet得到segment
  3. 对B应用DensePose得到IUV
  4. 对两个candidate、两个subset、两个segment、一个IUV以及图A、B应用CT-Net即可得到换装后的结果

Resource

  1. 上图的集成了所有功能的exe程序,可以从这里,提取码:6666获取,由于一共集成了4个模型,因此非常大,有1个多G,同时运行也很缓慢,大约要一分钟
  2. 该github工程仅包含代码,实际运行调试需要模型,可以从这里,提取码:6666获取,再放到对应的位置就好了
  3. 知乎分析文章:https://zhuanlan.zhihu.com/p/452366369

Content

将CVPR2021的服装迁移模型CT-Net搬运至NCNN框架上

CT-Net依赖
  1. 依赖OpenPose的人体姿势——pytorch实现
  2. 依赖LIP_JPPNet的的人体解析分割图——Tensorflow实现
  3. 依赖Densepose的人体IUV图——Detectron2实现
待完成&已完成
  • OpenPose的ncnn&c++实现 —— OpenPose文件夹
  • LIP_JPPNet的ncnn&c++实现 —— LIP_JPPNet文件夹
  • Densepose的ncnn&c++实现 —— DensePose文件夹
  • CT-Net的ncnn&c++实现 —— CT-Net文件夹
  • 组合四个模型的ncnn&c++实现 —— Ensemble文件夹
  • QT GUI实现 —— QT文件夹

Reference

  1. CT-Net
  2. OpenPose
  3. LIP_JPPNet
  4. Densepose
  5. Detectron2
  6. DenseSense
  7. ncnn
  8. opencv-mobile
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].