graspnet/graspnetAPI

Toolbox for our GraspNet-1Billion dataset.

What it solves

It provides a standardized API for interacting with the GraspNet-1Billion dataset, a large-scale benchmark for general object grasping in robotics. This allows researchers to easily load, process, and validate grasp labels and point cloud data for training and evaluating grasping algorithms.

How it works

The library acts as a data interface that handles the loading of scene point clouds and grasp labels. It includes utility functions to convert between different grasp representations (6D and rectangle grasps) and tools to check the completeness of the dataset files.

Who it’s for

Robotics researchers and developers working on general object grasping and robotic manipulation.

Highlights

  • Standardized API for the GraspNet-1Billion dataset.
  • Support for 6D and rectangle grasp conversions.
  • Tools for loading scene point clouds and grasp labels.
  • Built-in data completeness checks and depth image inpainting.

Related

  • Project
    alibaba/GraphScope

    A unified distributed graph computing platform from Alibaba that enables interactive queries, graph analytics, and GNN training on large-scale graphs using a Python interface.

  • Project
    NVlabs/GraspGen

    A diffusion-based framework for 6-DOF robotic grasp generation that supports multiple gripper types and provides real-time, collision-aware grasp predictions from 3D point clouds or meshes.

  • Project
    graphistry/pygraphistry

    A Python library for high-performance graph visualization and analytics that leverages GPU acceleration and columnar data to handle millions of edges.

  • Project
    galilai-group/stable-worldmodel

    A platform for reproducible world model research and evaluation that provides a unified interface for data collection, training, and model-predictive control evaluation.

  • Project
    huggingface/datasets

    A lightweight library for easy one-line loading and efficient pre-processing of massive multi-modal datasets for machine learning training and evaluation.