An Exploration of Neural Radiance Field Scene Reconstruction: Synthetic, Real-world and Dynamic Scenes

TL;DR

This paper investigates neural radiance field techniques for 3D scene reconstruction across synthetic, real-world, and dynamic scenes, highlighting improvements in efficiency and extending capabilities to real-world dynamic environments.

Contribution

It introduces an extended D-NeRF approach capable of reconstructing real-world dynamic scenes, building upon existing synthetic scene methods and optimizing training and rendering times.

Findings

Multi-resolution hash encoding reduces training and rendering time.

NeRF-based methods can effectively reconstruct static and real-world scenes.

Extended D-NeRF handles real-world dynamic scene reconstruction.

Abstract

This project presents an exploration into 3D scene reconstruction of synthetic and real-world scenes using Neural Radiance Field (NeRF) approaches. We primarily take advantage of the reduction in training and rendering time of neural graphic primitives multi-resolution hash encoding, to reconstruct static video game scenes and real-world scenes, comparing and observing reconstruction detail and limitations. Additionally, we explore dynamic scene reconstruction using Neural Radiance Fields for Dynamic Scenes(D-NeRF). Finally, we extend the implementation of D-NeRF, originally constrained to handle synthetic scenes to also handle real-world dynamic scenes.