Block-NeRF: Scalable Large Scene Neural View Synthesis
This work addresses the challenge of scalable neural view synthesis for large scenes, representing an incremental improvement over existing NeRF methods.
The authors tackled the problem of scaling Neural Radiance Fields (NeRF) to large-scale environments by decomposing scenes into individually trained NeRFs, enabling rendering of city-scale scenes like a San Francisco neighborhood from 2.8 million images.
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 decompose 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.