This repository is a curated list of 3D vision papers relevant to the robotics domain, focusing on advancements in the era of large language and vision-language models. It serves researchers and practitioners by providing links to papers, code, and related websites, aiming to consolidate knowledge in this rapidly evolving field.

How It Works

The repository categorizes papers across key areas like Policy Learning, Pretraining, VLM/LLM integration, Representations, and Simulations/Datasets. It highlights recent research, including diffusion models for policy learning, 3D representations for visuomotor tasks, and the application of LLMs for robotic manipulation and spatial reasoning. The curated nature allows users to quickly identify state-of-the-art approaches and relevant resources.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required. Users can browse the linked papers and code repositories directly.

Highlighted Details

• Comprehensive coverage of recent (2023-2024) papers in 3D vision for robotics.
• Categorization includes Policy Learning, Pretraining, VLM/LLM, Representations, and Datasets.
• Links to papers, code, and webpages for each entry are provided.
• Includes relevant survey papers on topics like Neural Fields, LLMs in 3D, and 3D Gaussian Splatting.

Maintenance & Community

The list is curated and maintained by Zubair Irshad. Users are encouraged to submit pull requests or email additions.

Licensing & Compatibility

The repository itself is not software and does not have a license. Individual linked papers and code repositories will have their own licenses.

Limitations & Caveats

This is a static list and does not include code for execution or experimentation. The rapidly evolving nature of the field means the list may not be exhaustive or immediately up-to-date with the very latest publications.