InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity
This enables efficient, scalable 3D rendering for applications like virtual navigation, though it is incremental as it adapts existing mesh-based LoD methods to NeRF.
The paper tackles the problem of scaling Neural Radiance Fields (NeRF) to large scenes by introducing an octree-based Level of Detail (LoD) technique, achieving rendering with O(log n) space complexity and training with O(n) complexity.
The conventional mesh-based Level of Detail (LoD) technique, exemplified by applications such as Google Earth and many game engines, exhibits the capability to holistically represent a large scene even the Earth, and achieves rendering with a space complexity of O(log n). This constrained data requirement not only enhances rendering efficiency but also facilitates dynamic data fetching, thereby enabling a seamless 3D navigation experience for users. In this work, we extend this proven LoD technique to Neural Radiance Fields (NeRF) by introducing an octree structure to represent the scenes in different scales. This innovative approach provides a mathematically simple and elegant representation with a rendering space complexity of O(log n), aligned with the efficiency of mesh-based LoD techniques. We also present a novel training strategy that maintains a complexity of O(n). This strategy allows for parallel training with minimal overhead, ensuring the scalability and efficiency of our proposed method. Our contribution is not only in extending the capabilities of existing techniques but also in establishing a foundation for scalable and efficient large-scale scene representation using NeRF and octree structures.