This repository serves as a comprehensive, curated collection of resources for 3D machine learning, targeting researchers and practitioners in computer vision, graphics, and ML. It aims to consolidate papers, datasets, and courses related to various 3D data representations and tasks, facilitating easier access and understanding of the rapidly evolving field.

How It Works

The repository organizes research papers and datasets by 3D data representation (e.g., point clouds, volumetric, meshes) and task (e.g., segmentation, pose estimation, synthesis). It uses icons to denote different 3D representations and provides links to external resources like Connected Papers for visualizing research landscapes. The project encourages community contributions via pull requests or issues.

Quick Start & Requirements

This is a curated list of resources, not a runnable software package. No installation or specific requirements are listed.

Highlighted Details

• Extensive catalog of over 50 datasets relevant to 3D ML, including large-scale benchmarks like ShapeNet, ScanNet, and Matterport3D.
• Comprehensive listing of academic courses from top universities covering 3D data and machine learning.
• Categorized bibliography of research papers across numerous 3D ML tasks, from single-object classification to scene synthesis.
• Includes links to code repositories for many listed papers, enabling practical experimentation.

Maintenance & Community

The repository is maintained by timzhang642 and actively encourages community involvement. A Slack workspace is available for discussion and collaboration.

Licensing & Compatibility

The repository itself does not have a specified license, but it links to numerous research papers and datasets, each with their own licenses. Users must adhere to the individual licenses of the linked resources.

Limitations & Caveats

This repository is a curated list and does not provide any executable code or integrated tools. The quality and availability of linked resources are dependent on their original sources.