A Survey on 3D Gaussian Splatting

By Guikun Chen, Wenguan Wang. ACM Computing Surveys, 2024

355 citations recorded by the source corpus.

3D Gaussian splatting (GS) has emerged as a transformative technique in radiance fields. Unlike mainstream implicit neural models, 3D GS uses millions of learnable 3D Gaussians for an explicit scene representation. Paired with a differentiable rendering algorithm, this approach achieves real-time rendering and unprecedented editability, making it a potential game-changer for 3D reconstruction and representation. In the present article, we provide the first systematic overview of the recent developments and critical contributions in 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.

Subfields: Atomic and Molecular Physics, and Optics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a6e46344388dc3686bff3efb78ba75790ce11cd6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

Gordon Wetzstein

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting (2023, neutral): “Novel view synthesis (NVS) from a set of view collections, as demonstrated by recent works [16, 35, 46], has played a critical role in the domain of 3D vision and is pivotal in many applications, e.g., VR/AR and autonomous driving.”
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering (2023, methodology): “As introduced by [47], using a viewing transform denoted as W and the Jacobian of the affine approximation of the projective transformation represented by J , the co-variance matrix Σ ′ in camera coordinates can be computed as follows: In summary, each Gaussian point is characterized by the…”
GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation (2024, background): “This representation has been quickly adopted for various application, including image-or text-conditioned 3D [14,47,49] and 4D generation [52,74], avatar reconstruction [31,48,72,76,113], dynamic scene reconstruction [61,102,107,108], among others [11,21,97].”
gsplat: An Open-Source Library for Gaussian Splatting (2024, neutral): “Gaussian Splatting, a seminal work proposed by Kerbl et al. (2023) is a rapidly developing area of research for high ﬁdelity 3D scene reconstruction and novel view synthesis with wide interest in both academia and industry (Fei et al., 2024; Chen and Wang, 2024; Bao et al., 2024; Wu et al., 2024).”
Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (2023, methodology): “Dynamic 3D Gaussians Our method is also inspired by Kerbl et al. (2023).”
Recent advances in 3D Gaussian splatting (2024, neutral): “As shown in Fig.”
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation (2024, methodology): “We specifically discuss recent methods in generation tasks using Gaussian splatting [4,7,23,38,56].”