Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Review

Anurag Dalal, Daniel Hagen, Kjell G. Robbersmyr, Kristian Muri Knausgård

TL;DR

An overview of recent developments in the Gaussian Splatting method is provided, covering input types, model structures, output representations, and training strategies, including the generation of novel, unseen views.

Abstract

Image-based 3D reconstruction is a challenging task that involves inferring the 3D shape of an object or scene from a set of input images. Learning-based methods have gained attention for their ability to directly estimate 3D shapes. This review paper focuses on state-of-the-art techniques for 3D reconstruction, including the generation of novel, unseen views. An overview of recent developments in the Gaussian Splatting method is provided, covering input types, model structures, output representations, and training strategies. Unresolved challenges and future directions are also discussed. Given the rapid progress in this domain and the numerous opportunities for enhancing 3D reconstruction methods, a comprehensive examination of algorithms appears essential. Consequently, this study offers a thorough overview of the latest advancements in Gaussian Splatting.

Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Review

TL;DR

An overview of recent developments in the Gaussian Splatting method is provided, covering input types, model structures, output representations, and training strategies, including the generation of novel, unseen views.

Abstract

Image-based 3D reconstruction is a challenging task that involves inferring the 3D shape of an object or scene from a set of input images. Learning-based methods have gained attention for their ability to directly estimate 3D shapes. This review paper focuses on state-of-the-art techniques for 3D reconstruction, including the generation of novel, unseen views. An overview of recent developments in the Gaussian Splatting method is provided, covering input types, model structures, output representations, and training strategies. Unresolved challenges and future directions are also discussed. Given the rapid progress in this domain and the numerous opportunities for enhancing 3D reconstruction methods, a comprehensive examination of algorithms appears essential. Consequently, this study offers a thorough overview of the latest advancements in Gaussian Splatting.
Paper Structure (40 sections, 12 equations, 2 figures, 2 tables)

This paper contains 40 sections, 12 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. A primer on 3D Reconstruction and Novel View Synthesis
  3. 3D Data Representation
  4. Traditional Approaches
  5. Novel Approaches
  6. Datasets
  7. 3D reconstruction and NVS techniques
  8. Fundamentals of Gaussian Splatting
  9. Mathematical Representation and Rendering process
  10. Projection of Gaussians
  11. Depth Compositing of Gaussians
  12. Quality Assessment Matrices
  13. Peak Signal to Noise Ratio
  14. Structural Similarity Index Measure
  15. Learned Perceptual Image Patch Similarity
  16. ...and 25 more sections

Figures (2)

  • Figure 1: Taxonomy of selected key Gaussian Splatting innovation papers, selected using a combination of citations and GitHub star rating.
  • Figure 2: Dynamic and deformation based methods.