Coder Social home page Coder Social logo

jiahaoplus / saga Goto Github PK

View Code? Open in Web Editor NEW
67.0 67.0 3.0 233.7 MB

[ECCV 2022] SAGA: Stochastic Whole-Body Grasping with Contact

Home Page: https://jiahaoplus.github.io/SAGA/saga.html

License: MIT License

Python 100.00%
generative-model grasping hand-object-interaction hand-pose human-motion human-object-interaction human-pose motion-generation motion-synthesis vae

saga's People

Contributors

jiahaoplus avatar wuyan01 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

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

saga's Issues

A possible bug in fittingop

o2h_marker, h2o_signed_marker, o2h_idx_marker, _ = point2point_signed(body_markers_rec, verts_object.float(), normal_object.float())
o2h_signed, h2o_signed, o2h_idx, _ = point2point_signed(rhand_verts_rec, verts_object.float(), rh_normals, normal_object.float())

In line 183, it seems that the third positional argument should be the normals of markers.

subject shape not fixed

hi there, thank you for the interesting work. I have a question related to stage 1 the grasppose generation. Noted that given different height of the objects, the inference of huamn boy shape is different, is there a way to keep the same person shape and only infer different pose?

thanks.

Training script for separate localmotion infill pretraining.

Hi @JiahaoPlus, @wuyan01

Currently, train_graspmotion.py has code for combined training of TrajFill and LocalMotionFill models.
Can you please provide the script for training the LocalMotionFill model separately on AMASS?

While training the LocalMotionFill model separately on AMASS, the trajectory input will be the ground truth trajectory of the motion, right?

Thanks!

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.