Learning-based Ray Sampling Strategy for Computation Efficient Neural Radiance Field Generation

The neural radiance field (NeRF) constructs an implicit representation function to substitute the traditional 3D representation, such as point cloud, mesh, and voxels, leading to consistent and efficient image rendering at desired observing spatial position. However, NeRF requires dense sampling in 3D space to build the continuous representation function. The huge amount of sampling points occupies intensive computing resources, which hinders NeRF from being integrated into the lightweight system. In this paper, we present a learning-based sampling strategy, which conducts dense sampling in regions with rich texture and sparse sampling in other regions, extremely reducing the computation resources and accelerating the learning speed. Furthermore, to alleviate the additional computation overhead caused by the proposed sampling strategy, we present a distributed structure to conduct the sampling decision individually. The distributed design releases the computation burden on the devices, which enables the deployment of the proposed strategy to the practical systems.