Code Monkey home page Code Monkey logo

deepsketch2face's Introduction

DeepSketch2Face

Note: The database and the full progame code are not publicly available at the moment under patent protection and other authors' interest.

Demo of DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling. Logo We use Caffe modified from Microsoft/Caffe. Default Development OS is Windows 10 x64.

Demo (Pure Alexnet Version)

  1. Download repo here
  2. Download caffemodel and dlls and expand to $(this_repo)\demo
  3. Install CUDA v8.0 (into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0). Other versions may not be supported.
  4. Run $(this_repo)\demo\deepsketch2face.exe

Demo (With bilinear encoding)

Not available

Database

Please contact [email protected] for the database.

Source Code Reproduction

May not be uploaded.

  1. Download source repo here
  2. Install Visual Studio 2013 Ultimate
  3. Install CUDA v8.0 (into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0) and cudnn v5.1 (copy files into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\cuda). Other versions may not be supported.
  4. Build $(this_repo)\tools\caffe-master\windows\Caffe.sln in Release x64. If there are errors, check if step 2 is correctly done.
  5. Install Qt 5.8 (VS2013 x64). Other versions may not be supported.
  6. If you use different Qt and Visual Studio version, you need to rebuild $(this_repo)\tools\libQGLViewer\QGLViewer in Qt Creator.
  7. In $(this_repo)\tools\caffe-master\include\caffe\proto\caffe.pb.h, change "STRICT" in line 2525 and 9794 into "_STRICT"
  8. Open $(this_repo)\src\deepsketch2face.pro in Qt Creator, set build directory to $(this_repo)\build, then build the program in Release.
  9. Copy $(this_repo)\build\release\deepsketch2face.exe into $(this_repo)\demo
  10. For all .dll file in $(this_repo)\demo and $(this_repo)\demo\platforms, if you build the program in different settings, you may need to change them correspondingly. A safe but redundant move is to copy all .dll file in $(this_repo)\tools\ and Qt here.
  11. Run $(this_repo)\demo\deepsketch2face.exe

deepsketch2face's People

Contributors

changgyhub avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

deepsketch2face's Issues

some questions

Hi authors of deepsketh2face,when reading your paper i meet some problems.
In the chapter 4.3-Network Architecture you mentioned 66 coefficients in shape-level input.
I'm confused about how to get these 66 coefficients from my input sketch.
I'd appreciate if you can help me .My email is [email protected],thanks!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.