Code Monkey home page Code Monkey logo

zjumocao_selfmade_dataset's Introduction

网址:

  1. EasyMocap
  2. Neural_body
  3. Animatable_nerf

前提:

  • .26 服务器运行EasyMocap(/home/zhaozisong/EasyMocap/)时:
conda activate fenerf   #确保进入fenerf环境运行
export PYOPENGL_PLATFORM=osmesa
  • 运行Animatable_nerf时:
conda activate animatable_nerf

步骤:

EasyMocap预估图片关键点信息教程参考网址

  1. 先用设置data路径
data=/home/zhaozisong/EasyMocap/data/new/
  1. 推荐用Mediapipe:
#Run the detection of full body:
python3 apps/preprocess/extract_keypoints.py ${data} --mode mp-holistic

EasyMocap预估SMPL参数

  1. 提取extri和intri配置文件&&预估单目视频的SMPL参数
#单目视频
#提取extri和intri配置文件不需要跑完程序 只需要获取到extri和intri配置文件就可停止
#预估单目视频的SMPL参数需要跑完整个程序
python3 apps/demo/mocap.py ${data} --work internet
  1. 预估多目视频的SMPL参数
#多目视频 ranges:0-图片的最大值
python3 apps/demo/mocap.py ${data} --work lightstage-dense-smpl --subs_vis 01 --ranges 0 800 1

得到output-smpl-3d\文件夹下的全部文件。

脚本提取预估的SMPL参数获取params和vertives

  1. 脚本处理得到的output-smpl-3d/smpl文件夹下的.json文件,获取params和vertices

    #generate params and vertices
    python easymocap_to_neuralbody.py --input_dir {data_dir} --type vertices
    

    问题:

  • 目前存在的问题是 脚本得到的params和vertices维度和最终需要的对应不上。
  • 肉眼对比与numpy.shape和可运行的数据集完全一致
  • params需要修改脚本的代码自己保存
  • 怀疑是代码脚本代码的问题

脚本获取annots.npy

  1. 脚本获取annots.npy
    #generate annots.npy
    python easymocap_to_neuralbody.py --input_dir {data_dir} --type annots
    

EasyMocap获取图片mask

# render mask
python3 apps/postprocess/render.py ${data} --exp output-smpl-3d --mode instance-d0.05 --ranges 0 1400 1

脚本获取lbs文件夹下的相关文件

  1. 脚本a脚本b分别来获取和lbs相关的.npy文件

    问题:

    • 也是因为params和vertices的问题处理不了
    • 需要的维度为 23x3x3
    • 输入的为 24x3x1

结束


zjumocao_selfmade_dataset's People

Contributors

13136983989 avatar

Watchers

 avatar

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.