This repository serves as a companion to a survey paper on "Forging Vision Foundation Models for Autonomous Driving," offering a curated collection of research papers, methodologies, and insights into the challenges and opportunities in this domain. It is a valuable resource for researchers and practitioners looking to understand and implement state-of-the-art techniques in applying foundation models to autonomous driving systems.

How It Works

The repository categorizes relevant research papers across key areas such as Data Preparation, GANs, Diffusion models, NeRFs, 3D Gaussian Splatting, Self-supervised Training, Distillation, Rendering, World Models, and Adaptation. Each paper entry includes an abstract and a representative figure, providing a quick overview of its core concepts and contributions. The project aims to track progress and serve as a quick reference for implementing associated methods.

Quick Start & Requirements

This repository is a curated list of papers and does not contain executable code for direct installation or running. The primary requirement is access to the cited research papers, which are typically available via arXiv or other academic repositories.

Highlighted Details

• Comprehensive taxonomy of foundation models for autonomous driving.
• Detailed summaries and figures for over 40 research papers.
• Focus on challenges, methodologies, and future research directions.
• Continuous updates to track advancements in the field.

Maintenance & Community

The repository is maintained by the authors of the survey paper and welcomes contributions via Pull Requests, issues, or emails. The project is actively updated, with recent additions including papers on 3DGS and related surveys.

Licensing & Compatibility

The repository itself does not specify a license, but it references and links to various research papers, each with its own licensing and usage terms. Compatibility for commercial use would depend on the licenses of the individual papers and their associated codebases.

Limitations & Caveats

This repository is a curated list of research papers and does not provide a unified codebase or framework for direct implementation. Users will need to access and implement the individual methods described in the cited papers.