# Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?

arXiv: https://arxiv.org/abs/2502.19318 · HTML: https://mlsanity.com/paper/2502.19318/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 22 of 22)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Differentiable Surface Splatting for Point-based Geometry Processing](https://mlsanity.com/paper/1906.04173/) (2019)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes](https://mlsanity.com/paper/2302.12249/) (2023)
- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2311.16728/) (2023)
- [3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes](https://mlsanity.com/paper/2407.07090/) (2024)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering](https://mlsanity.com/paper/2402.00525/) (2024)
- [Differentiable Point-Based Radiance Fields for Efficient View Synthesis](https://mlsanity.com/paper/2205.14330/) (2022)
- [SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration](https://mlsanity.com/paper/2312.07541/) (2023)
- [Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Review](https://mlsanity.com/paper/2405.03417/) (2024)
- [On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy](https://mlsanity.com/paper/2402.00752/) (2024)
- [Don't Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Media](https://mlsanity.com/paper/2405.15425/) (2024)
- [Gaussian Shadow Casting for Neural Characters](https://mlsanity.com/paper/2401.06116/) (2024)
- [Unified Gaussian Primitives for Scene Representation and Rendering](https://mlsanity.com/paper/2406.09733/) (2024)

## Built on by (most cited first, 19 of 19)

- [Faster-GS: Analyzing and Improving Gaussian Splatting Optimization](https://mlsanity.com/paper/2602.09999/) (2026)
- [AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering](https://mlsanity.com/paper/2504.12811/) (2025)
- [Surgical Gaussian Surfels: Highly Accurate Real-time Surgical Scene Rendering using Gaussian Surfels](https://mlsanity.com/paper/2503.04079/) (2025)
- [3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras](https://mlsanity.com/paper/2505.24053/) (2025)
- [Splat the Net: Radiance Fields with Splattable Neural Primitives](https://mlsanity.com/paper/2510.08491/) (2025)
- [From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians](https://mlsanity.com/paper/2604.07337/) (2026)
- [RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting](https://mlsanity.com/paper/2508.04078/) (2025)
- [UGOD: Uncertainty-Guided Differentiable Opacity and Soft Dropout for Enhanced Sparse-View 3DGS](https://mlsanity.com/paper/2508.04968/) (2025)
- [UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting](https://mlsanity.com/paper/2506.05011/) (2025)
- [Moment-Based 3D Gaussian Splatting: Resolving Volumetric Occlusion with Order-Independent Transmittance](https://mlsanity.com/paper/2512.11800/) (2025)
- [RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis](https://mlsanity.com/paper/2509.07782/) (2025)
- [From Volume Rendering to 3D Gaussian Splatting: Theory and Applications](https://mlsanity.com/paper/2510.18101/) (2025)
- [The Impact and Outlook of 3D Gaussian Splatting](https://mlsanity.com/paper/2510.26694/) (2025)
- [EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing](https://mlsanity.com/paper/2601.23065/) (2026)
- [OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS](https://mlsanity.com/paper/2511.09397/) (2025)
- [Generalized non-exponential Gaussian splatting](https://mlsanity.com/paper/2603.02887/) (2026)
- [Learning View-Dependent Splatting Kernels](https://mlsanity.com/paper/2605.25426/) (2026)
- [CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation](https://mlsanity.com/paper/2608.20803/) (2026)
- [UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian Splatting](https://mlsanity.com/paper/2609.39089/) (2026)

## Abstract (arXiv)

Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real-time novel-view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray-marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in-depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.