Improving Neural Radiance Field using Near-Surface Sampling with Point Cloud Generation

TL;DR

This paper introduces a near-surface sampling method for Neural Radiance Fields that leverages scene geometry to enhance rendering quality and reduce training time by focusing sampling around estimated object surfaces.

Contribution

It proposes a novel near-surface sampling framework that estimates scene geometry using depth images and point clouds, significantly improving NeRF rendering quality and training efficiency.

Findings

Enhanced rendering quality compared to original NeRF and state-of-the-art methods

Significant reduction in training time for NeRF models

Effective scene geometry estimation using depth images and point clouds

Abstract

Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time since it samples many 3D points. In addition, if one samples points from occluded regions or in the space where an object is unlikely to exist, the rendering quality of NeRF can be degraded. These issues can be solved by estimating the geometry of 3D scene. This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To this end, the proposed method estimates the surface of a 3D object using depth images of the training set and sampling is performed around there only. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud. Experimental results show that the proposed near-surface sampling NeRF framework can significantly improve the rendering quality, compared to the original NeRF and three different state-of-the-art NeRF. In addition, one can significantly accelerate the training time of a NeRF model with the proposed near-surface sampling framework.