Survey on Fundamental Deep Learning 3D Reconstruction Techniques

TL;DR

This survey reviews key deep learning methods for 3D reconstruction, focusing on Neural Radiance Fields, Latent Diffusion Models, and 3D Gaussian Splatting, analyzing their algorithms, strengths, and future directions.

Contribution

It provides a comprehensive overview of fundamental DL-based 3D reconstruction techniques, dissecting algorithms and evaluating their tradeoffs and potential applications.

Findings

NeRFs enable photo-realistic 3D scene rendering.

LDMs offer flexible generative capabilities for 3D models.

3D Gaussian Splatting provides efficient real-time rendering.

Abstract

This survey aims to investigate fundamental deep learning (DL) based 3D reconstruction techniques that produce photo-realistic 3D models and scenes, highlighting Neural Radiance Fields (NeRFs), Latent Diffusion Models (LDM), and 3D Gaussian Splatting. We dissect the underlying algorithms, evaluate their strengths and tradeoffs, and project future research trajectories in this rapidly evolving field. We provide a comprehensive overview of the fundamental in DL-driven 3D scene reconstruction, offering insights into their potential applications and limitations.