构建了含复杂光照的城市场景数据集，助力自动驾驶与数字孪生研究
LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions
- 合成300+天空光照图，支持多光照条件模拟
- 覆盖5万张图像，含深度、法线、材质等丰富属性
- 为城市逆渲染任务提供基准测试与分析基础
城市场景的逆渲染对自动驾驶、数字孪生等应用至关重要，但受多重光照、间接光与阴影影响，仍面临挑战。由于缺乏合适数据集，这些因素对固有分解与三维重建的影响尚不明确。本文提出LightCity，一个高质量合成城市场景数据集，涵盖300余种可控天空光照图，覆盖街景与航拍视角，生成超过5万张图像，并包含深度、法线、材质、直接光与间接光等丰富属性。我们基于LightCity对三大城市环境基础任务进行基准测试与系统分析，为相关研究提供坚实基础。
原文摘要 · Abstract (English)
Inverse rendering in urban scenes is pivotal for applications like autonomous driving and digital twins. Yet, it faces significant challenges due to complex illumination conditions, including multi-illumination and indirect light and shadow effects. However, the effects of these challenges on intrinsic decomposition and 3D reconstruction have not been explored due to the lack of appropriate datasets. In this paper, we present LightCity, a novel high-quality synthetic urban dataset featuring diverse illumination conditions with realistic indirect light and shadow effects. LightCity encompasses over 300 sky maps with highly controllable illumination, varying scales with street-level and aerial perspectives over 50K images, and rich properties such as depth, normal, material components, light and indirect light, etc. Besides, we leverage LightCity to benchmark three fundamental tasks in the urban environments and conduct a comprehensive analysis of these benchmarks, laying a robust foundation for advancing related research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。