How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey

Fabio Tosi, Youmin Zhang, Ziren Gong, Erik Sandström, Stefano Mattoccia +2 more
2/20/2024
cs.CVcs.RO

No official code found. Best implementation: 3D-Vision-World/awesome-NeRF-and-3DGS-SLAM (2,131 stars, last commit 2026-04-27).

Abstract

Over the past two decades, research in the field of Simultaneous Localization and Mapping (SLAM) has undergone a significant evolution, highlighting its critical role in enabling autonomous exploration of unknown environments. This evolution ranges from hand-crafted methods, through the era of deep learning, to more recent developments focused on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) representations. Recognizing the growing body of research and the absence of a comprehensive survey on the topic, this paper aims to provide the first comprehensive overview of SLAM progress through the lens of the latest advancements in radiance fields. It sheds light on the background, evolutionary path, inherent strengths and limitations, and serves as a fundamental reference to highlight the dynamic progress and specific challenges.

View on arXivView PDF

Code Implementations(1)

3D-Vision-World/awesome-NeRF-and-3DGS-SLAMCommunity100%

A comprehensive list of Implicit Representations, NeRF and 3D Gaussian Splatting papers relating to SLAM/Robotics domain, including papers, videos, codes, and related websites

2,131150Dec 8, 20225 months ago
3dgsawesomegaussiansplattinglidar-slamnerf+3 more

Similar Papers

The Impact and Outlook of 3D Gaussian Splatting

83% match2025

Advances in 4D Representation: Geometry, Motion, and Interaction

82% match2025

Deep Learning on 3D Semantic Segmentation: A Detailed Review

81% match1 repo262024

The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering

81% match2025

A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond

81% match1 repo2822024

Mastering AI: Big Data, Deep Learning, and the Evolution of Large Language Models -- AutoML from Basics to State-of-the-Art Techniques

80% match2024

Cite this paper

@article{tosi2024nerfs,
  title  = {How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey},
  author = {Fabio Tosi and Youmin Zhang and Ziren Gong and Erik Sandström and Stefano Mattoccia and Martin R. Oswald and Matteo Poggi},
  year   = {2024},
  eprint = {2402.13255},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.13255v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.13255.svg)](https://codeofpaper.com/paper/2402.13255)

Discussion