Loading [a11y]/accessibility-menu.js
MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond | IEEE Conference Publication | IEEE Xplore

MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond

Publisher: IEEE

Abstract:

Neural radiance fields (NeRF) and its subsequent variants have led to remarkable progress in neural rendering. While most of recent neural rendering works focus on object...View more

Abstract:

Neural radiance fields (NeRF) and its subsequent variants have led to remarkable progress in neural rendering. While most of recent neural rendering works focus on objects and small-scale scenes, developing neural rendering methods for city-scale scenes is of great potential in many real-world applications. However, this line of research is impeded by the absence of a comprehensive and high-quality dataset, yet collecting such a dataset over real city-scale scenes is costly, sensitive, and technically infeasible. To this end, we build a large-scale, comprehensive, and high-quality synthetic dataset for city-scale neural rendering researches. Leveraging the Unreal Engine 5 City Sample project, we developed a pipeline to easily collect aerial and street city views, accompanied by ground-truth camera poses and a range of additional data modalities. Flexible controls on environmental factors like light, weather, human and car crowd are also available in our pipeline, supporting the need of various tasks covering city-scale neural rendering and beyond. The resulting pilot dataset, MatrixCity, contains 67k aerial images and 452k street images from two city maps of total size 28km 2 . On top of MatrixCity, a thorough benchmark is also conducted, which not only reveals unique challenges of the task of city-scale neural rendering, but also highlights potential improvements for future works. The dataset and code will be publicly available at the project page: https://city-super.github.io/matrixcity/.
Date of Conference: 01-06 October 2023
Date Added to IEEE Xplore: 15 January 2024
ISBN Information:

ISSN Information:

Publisher: IEEE
Conference Location: Paris, France

Funding Agency:

No metrics found for this document.

1. Introduction

Realistic rendering of city-scale scenes is a crucial component of many real-world applications, including aerial surveying, virtual reality, film production, and gaming. While NeRF [22] has made notable advancements in rendering objects and small-scale scenes, only a few early attempts [30], [33], [37] have sought to extend NeRF and its variants to larger city-scale scenes. Due to the paucity of benchmark dataset, the complexity and challenges of city-scale neural rendering have not been thoroughly investigated.

Usage
Select a Year
2024

View as

Total usage sinceJan 2024:42
024681012JanFebMarAprMayJunJulAugSepOctNovDec3102535232250
Year Total:42
Data is updated monthly. Usage includes PDF downloads and HTML views.

References

References is not available for this document.