RGB-D Neural Radiance Fields: Local Sampling for Faster Training

TL;DR

This paper introduces an RGB-D based neural radiance field method that uses depth-guided local sampling and a smaller network to significantly reduce training time while maintaining high-quality 3D scene representations.

Contribution

It presents a novel depth-guided local sampling strategy and a compact neural network architecture for faster NeRF training using RGB-D data.

Findings

Training time is reduced by leveraging depth information.

The proposed method maintains high-quality scene reconstruction.

Faster training does not compromise the accuracy of geometry.

Abstract

Learning a 3D representation of a scene has been a challenging problem for decades in computer vision. Recent advances in implicit neural representation from images using neural radiance fields(NeRF) have shown promising results. Some of the limitations of previous NeRF based methods include longer training time, and inaccurate underlying geometry. The proposed method takes advantage of RGB-D data to reduce training time by leveraging depth sensing to improve local sampling. This paper proposes a depth-guided local sampling strategy and a smaller neural network architecture to achieve faster training time without compromising quality.