Block-NeRF: Scalable Large Scene Neural View Synthesis

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 8238 - 8248
• Main Authors: Tancik, Matthew, Casser, Vincent, Yan, Xinchen, Pradhan, Sabeek, Mildenhall, Ben P., Srinivasan, Pratul, Barron, Jonathan T., Kretzschmar, Henrik
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2022
• Subjects: 3D from multi-view and sensors; Photogrammetry and remote sensing; Vision applications and systems; Buildings; Computer architecture; Computer vision; Image reconstruction; Pattern recognition; Rendering (computer graphics); Transient analysis
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52688.2022.00807

We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments. Specifically, we demonstrate that when scaling NeRF to render city-scale scenes spanning multiple blocks, it is vital to de-compose the scene into individually trained NeRFs. This decomposition decouples rendering time from scene size, enables rendering to scale to arbitrarily large environments, and allows per-block updates of the environment. We adopt several architectural changes to make NeRF robust to data captured over months under different environmental conditions. We add appearance embeddings, learned pose refinement, and controllable exposure to each individual NeRF, and introduce a procedure for aligning appearance between adjacent NeRFs so that they can be seamlessly combined. We build a grid of Block-NeRFs from 2.8 million images to create the largest neural scene representation to date, capable of rendering an entire neighborhood of San Francisco.