This paper presents an online system for large-scale and fine-grained 3D reconstruction using voxel hashing. The system efficiently fuses live depth maps into a single 3D model, achieving real-time performance without compromising quality or scale. The key innovation is a spatial hashing scheme that compresses space and allows for real-time access and updates of implicit surface data, without the need for a regular or hierarchical grid data structure. Surface data is stored densely only where measurements are observed, and data can be streamed efficiently in or out of the hash table, enabling scalability during sensor motion. The system is demonstrated to reconstruct a variety of scenes, including both fine-grained details and large-scale environments, with interactive rates on commodity graphics hardware. The authors compare their method to current state-of-the-art systems, showing improved performance and reconstruction quality.This paper presents an online system for large-scale and fine-grained 3D reconstruction using voxel hashing. The system efficiently fuses live depth maps into a single 3D model, achieving real-time performance without compromising quality or scale. The key innovation is a spatial hashing scheme that compresses space and allows for real-time access and updates of implicit surface data, without the need for a regular or hierarchical grid data structure. Surface data is stored densely only where measurements are observed, and data can be streamed efficiently in or out of the hash table, enabling scalability during sensor motion. The system is demonstrated to reconstruct a variety of scenes, including both fine-grained details and large-scale environments, with interactive rates on commodity graphics hardware. The authors compare their method to current state-of-the-art systems, showing improved performance and reconstruction quality.