3D Gaussian splatting (GS) has emerged as a transformative technique in explicit radiance field and computer graphics.This innovative approach, characterized by the use of millions of learnable 3D Gaussians, represents a significant departure from mainstream neural radiance field approaches, which predominantly use implicit, coordinate-based models to map spatial coordinates to pixel values.3D GS, with its explicit scene representation and differentiable rendering algorithm, not only promises real-time rendering capability but also introduces unprecedented levels of editability.This positions 3D GS as a potential game-changer for the next generation of 3D reconstruction and representation.In the present paper, we provide the first systematic overview of the recent developments and critical contributions in the domain of 3D GS.We begin with a detailed exploration of the underlying principles and the driving forces behind the emergence of 3D GS, laying the groundwork for understanding its significance.A focal point of our discussion is the practical applicability of 3D GS.By enabling unprecedented rendering speed, 3D GS opens up a plethora of applications, ranging from virtual reality to interactive media and beyond.This is complemented by a comparative analysis of leading 3D GS models, evaluated across various benchmark tasks to highlight their performance and practical utility.The survey concludes by identifying current challenges and suggesting potential avenues for future research.Through this survey, we aim to provide a valuable resource for both newcomers and seasoned researchers, fostering further exploration and advancement in explicit radiance field.
This survey presents a comprehensive overview of 3D Gaussian Splatting (3D GS), a transformative technique in explicit radiance fields and computer graphics. It contrasts the limitations of implicit models like Neural Radiance Fields (NeRF) with the benefits of using learnable 3D Gaussians for scene representation, enabling real-time rendering and high editability. The paper systematically explores the principles underlying 3D GS, its applications ranging from virtual reality to autonomous driving, and discusses performance comparisons of leading models. It identifies challenges faced by the technology and suggests future research directions, emphasizing the need for improved optimization algorithms and the integration of physics and semantics within 3D scene representations. By providing insights into 3D GS, this survey aims to inform both newcomers and experienced researchers in the field.
This paper employs the following methods:
- 3D Gaussian Splatting
- Differentiable Rendering
- Raymarching
The following datasets were used in this research:
- Replica
- D-NeRF
- ZJU-MoCap
- EndoNeRF
- 3D GS offers real-time rendering capability
- 3D GS enables unprecedented levels of editability
- 3D GS outperforms NeRF-based methods in various benchmarks
The authors identified the following limitations:
- Number of GPUs: None specified
- GPU Type: None specified