Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Neural Radiance Field Image Refinement through End-to-End Sampling Point Optimization

Kazuhiro Ohta, Satoshi Ono

TL;DR

A method is proposed that optimizes sampling points to reduce artifacts and produce more detailed images in NeRF, capable of synthesizing high‐quality novel viewpoint images.

Abstract

Neural Radiance Field (NeRF), capable of synthesizing high-quality novel viewpoint images, suffers from issues like artifact occurrence due to its fixed sampling points during rendering. This study proposes a method that optimizes sampling points to reduce artifacts and produce more detailed images.

Neural Radiance Field Image Refinement through End-to-End Sampling Point Optimization

TL;DR

A method is proposed that optimizes sampling points to reduce artifacts and produce more detailed images in NeRF, capable of synthesizing high‐quality novel viewpoint images.

Abstract

Neural Radiance Field (NeRF), capable of synthesizing high-quality novel viewpoint images, suffers from issues like artifact occurrence due to its fixed sampling points during rendering. This study proposes a method that optimizes sampling points to reduce artifacts and produce more detailed images.

Paper Structure

This paper contains 8 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. The proposed method
  4. Key idea
  5. Overview of the proposed method
  6. Structure of the sampling module
  7. Evaluation
  8. Conclusions

Figures (2)

  • Figure 1: Structure of the proposed method.
  • Figure 4: Examples of rendered images for test view on Real Foward-Facing dataset.