This repository is a curated list of research papers, projects, and resources focused on Text-to-3D and Diffusion-to-3D generation. It serves as a comprehensive reference for researchers and practitioners in the field of 3D content creation from natural language prompts and diffusion models.

How It Works

The project functions as an extensive bibliography, categorizing and linking to a wide array of academic papers and their associated codebases, project pages, and citations. It aims to provide a structured overview of the rapidly evolving landscape of 3D generative AI, covering various approaches and techniques.

Quick Start & Requirements

This repository is a curated list and does not have a direct installation or execution command. Users are expected to navigate the links provided to access individual project repositories, which will have their own setup instructions and dependencies.

Highlighted Details

• Extensive coverage of Text-to-3D and Diffusion-to-3D research, with over 200 linked papers.
• Categorization of methods based on input conditioning (e.g., text-only, image-to-3D, avatar generation).
• Includes links to project pages, code repositories, and BibTeX citations for each entry.
• Features a section on relevant datasets and frameworks in the field.

Maintenance & Community

The repository is actively updated, with recent additions in early 2024. It is inspired by the "awesome-NeRF" repository, suggesting a connection to the broader NeRF and 3D vision community.

Licensing & Compatibility

The repository itself is a list of links and does not impose a specific license. Individual projects linked within will have their own licenses.

Limitations & Caveats

This is a curated list and does not provide any executable code or unified framework. Users must individually explore and set up each project they are interested in. The rapid pace of research means the list is constantly growing and may not always be exhaustive.