This repository is a curated list of research papers on 3D Artificial Intelligence Generated Content (AIGC), serving as a comprehensive resource for researchers and practitioners in the field. It aims to track the rapid advancements in 3D generation techniques, providing a structured overview of key papers, methodologies, and emerging trends.

How It Works

The list is organized by paper category, including survey papers, benchmarks, specific generative methods (e.g., native, 2D prior-based, hybrid), and application areas like scene generation, human avatars, and dynamic content. It also includes sections for company involvement, implementations, and relevant talks, offering a holistic view of the 3D AIGC landscape.

Quick Start & Requirements

This is a curated list of papers and does not involve direct code execution or installation. Links to official repositories and bibtex citations are provided for each paper.

Highlighted Details

• Comprehensive coverage of 3D AIGC, from foundational concepts to state-of-the-art techniques.
• Categorization of papers by methodology (e.g., SDS, Diffusion Transformers, Gaussian Splatting) and application domain.
• Inclusion of links to GitHub repositories, demos, and bibtex for easy access and reproducibility.
• Tracking of industry trends with a list of companies actively involved in 3D generation.

Maintenance & Community

The project is maintained by hitcslj and is open to community contributions via pull requests. Contact information is provided for inquiries.

Licensing & Compatibility

The repository itself is released under the MIT license. Individual papers retain their original licenses.

Limitations & Caveats

As a curated list, it reflects the state of research at the time of its last update and may not include the absolute latest publications. The rapid pace of AIGC research means new methods are constantly emerging.