[Paper Review] NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)

Kyle Gao, Yina Gao+4 more|ArXiv.org|Oct 1, 2022

Robotics and Sensor-Based Localization105 citations

TL;DR

The provided text is a guide to IEEEtran LaTeX templates and submission practices, not an actual NeRF review paper.

ABSTRACT

In March 2020, Neural Radiance Field (NeRF) revolutionized Computer Vision, allowing for implicit, neural network-based scene representation and novel view synthesis. NeRF models have found diverse applications in robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, and more. In August 2023, Gaussian Splatting, a direct competitor to the NeRF-based framework, was proposed, gaining tremendous momentum and overtaking NeRF-based research in terms of interest as the dominant framework for novel view synthesis. We present a comprehensive survey of NeRF papers from the past five years (2020-2025). These include papers from the pre-Gaussian Splatting era, where NeRF dominated the field for novel view synthesis and 3D implicit and hybrid representation neural field learning. We also include works from the post-Gaussian Splatting era where NeRF and implicit/hybrid neural fields found more niche applications. Our survey is organized into architecture and application-based taxonomies in the pre-Gaussian Splatting era, as well as a categorization of active research areas for NeRF, neural field, and implicit/hybrid neural representation methods. We provide an introduction to the theory of NeRF and its training via differentiable volume rendering. We also present a benchmark comparison of the performance and speed of classical NeRF, implicit and hybrid neural representation, and neural field models, and an overview of key datasets.

Motivation & Objective

• Explain the purpose and scope of IEEEtran LaTeX templates and their limitations for final printing vs. IEEE Xplore submissions.
• Provide step-by-step instructions for creating common front matter, sections, and back matter in IEEE articles.
• Offer practical guidelines, examples, and a final checklist to ensure compliant submissions.

Proposed method

• Describe documentclass options for different IEEE publication types (journal, conference, compsoc, etc.).
• Show how to structure front matter (title, authors, abstract, keywords) and running headers.
• Provide templates and coding examples for figures, tables, equations, citations, lists, and biographical notes.
• Present guidance on LaTeX package usage and common pitfalls to avoid during submission.
• Include a final checklist to ensure numbering, cross-references, and formatting correctness.

Experimental results

Research questions

• RQ1 What are the recommended documentclass options for various IEEE publication types?
• RQ2 How should authors structure front matter and running heads in IEEE submissions?
• RQ3 What are the best practices for figures, tables, equations, and references in IEEEtran-based manuscripts?
• RQ4 What common mistakes should authors avoid when using LaTeX for IEEE submissions?

Key findings

• Provides a comprehensive inventory of IEEEtran features and commands for common publication elements.
• Outlines concrete examples for front matter, sections, figures, tables, equations, and references in IEEE style.
• Offers a practical checklist to minimize formatting errors and ensure compatibility with IEEE submission workflows.
• Highlights the distinction between draft templates and final IEEE Xplore-ready outputs and references the IEEE template selector.
• Recommends software distributions and online resources (TUG, TeX Live) for obtaining templates and support.