b:botstest.Submit a resource ↗

Models / Research

equidexflow · coenwerem

EquiDexFlow provides contact-grounded generative flows for dexterous grasping.

allegro-handcontact-modelingdexterous-graspingequivariant-neural-networksgenerative-models
Publisher repository ↗
equidexflow · coenwerem resource page screenshot
Resource screenshot · captured 2026-10-08 · visually reviewed

Overview

EquiDexFlow provides contact-grounded generative flows for dexterous grasping.

Publisher summary: “Contact-grounded SE(3)-equivariant dexterous grasp generative flows”

Use its repository to inspect the implementation, documentation and supported workflows. This directory record identifies the maintainer, code license and related resources; it does not claim that the project has been installed or tested on your robot.

Project information

Maintainer
coenwerem
Primary language
Python
Repository code license
MIT
Model-weight license
Not recorded
Dataset license
Not recorded
Hardware design license
Not recorded
Maintenance
Not archived in the last recorded metadata
Last observed repository push
2026-06-16

Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.

Documentation sections

  • EquiDexFlow
  • Quickstart
  • GPU machine: auto-detect the right CUDA wheel for the installed driver
  • CPU-only machine (no NVIDIA GPU): pull the CPU torch wheel and skip all nvidia- packages
  • -> out/demo/preview.png, out/demo/grasp{00..07}.npz
  • Installation

Browse this resource’s categories

Models / Grasping models ↗

Explore related collections

Browse Models →

More in Models