CULTURE3D: Cultural Landmarks and Terrain Dataset for 3D Applications

2025-01-12

AI Summary

Existing 3D reconstruction and analysis benchmarks lack large-scale, high-fidelity open datasets covering real-world cultural landmarks and complex terrains. To address this gap, we introduce the first globally collected, fine-grained UAV-based 3D dataset, systematically integrating diverse cultural heritage sites and natural landscapes. The dataset provides high-resolution imagery, precisely calibrated camera poses in COLMAP format, and unified interfaces for SfM, MVS, SLAM, NeRF, and Gaussian Splatting pipelines. It establishes the first open-world benchmark for fine-grained 3D modeling, enabling robust point cloud generation, semantic segmentation, and photorealistic reconstruction. Extensive evaluation across virtual tourism and digital twin applications demonstrates significant improvements in cross-method generalizability and geometric fidelity—achieving up to 28% higher PSNR and 35% lower Chamfer distance compared to prior benchmarks. This resource advances reproducible research in scalable, real-world 3D understanding.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

In this paper, we present a large-scale fine-grained dataset using high-resolution images captured from locations worldwide. Compared to existing datasets, our dataset offers a significantly larger size and includes a higher level of detail, making it uniquely suited for fine-grained 3D applications. Notably, our dataset is built using drone-captured aerial imagery, which provides a more accurate perspective for capturing real-world site layouts and architectural structures. By reconstructing environments with these detailed images, our dataset supports applications such as the COLMAP format for Gaussian Splatting and the Structure-from-Motion (SfM) method. It is compatible with widely-used techniques including SLAM, Multi-View Stereo, and Neural Radiance Fields (NeRF), enabling accurate 3D reconstructions and point clouds. This makes it a benchmark for reconstruction and segmentation tasks. The dataset enables seamless integration with multi-modal data, supporting a range of 3D applications, from architectural reconstruction to virtual tourism. Its flexibility promotes innovation, facilitating breakthroughs in 3D modeling and analysis.

Problem

• 3D Dataset
• Cultural Heritage
• Geographical Information

Innovation

• CULTURE3D
• 3D Reconstruction
• High-Definition Drone Imagery