# From NeRFs to Gaussian Splats, and Back

arXiv: https://arxiv.org/abs/2405.09717 · HTML: https://mlsanity.com/paper/2405.09717/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 15 May 2024.

## Builds on (most cited first, 25 of 25)

- [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)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)
- [DynIBaR: Neural Dynamic Image-Based Rendering](https://mlsanity.com/paper/2211.11082/) (2022)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding](https://mlsanity.com/paper/2311.18482/) (2023)
- [NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields](https://mlsanity.com/paper/2210.13641/) (2022)
- [Vision-Only Robot Navigation in a Neural Radiance World](https://mlsanity.com/paper/2110.00168/) (2021)
- [Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation](https://mlsanity.com/paper/2308.07931/) (2023)
- [RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS](https://mlsanity.com/paper/2403.13806/) (2024)
- [3D Neural Scene Representations for Visuomotor Control](https://mlsanity.com/paper/2107.04004/) (2021)
- [FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding](https://mlsanity.com/paper/2401.01970/) (2024)
- [vMAP: Vectorised Object Mapping for Neural Field SLAM](https://mlsanity.com/paper/2302.01838/) (2023)
- [NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields](https://mlsanity.com/paper/2210.04932/) (2022)
- [Beyond Uncertainty: Risk-Aware Active View Acquisition for Safe Robot Navigation and 3D Scene Understanding with FisherRF](https://mlsanity.com/paper/2403.11396/) (2024)
- [Customizable Perturbation Synthesis for Robust SLAM Benchmarking](https://mlsanity.com/paper/2402.08125/) (2024)

## Built on by (most cited first, 6 of 6)

- [Sources of Uncertainty in 3D Scene Reconstruction](https://mlsanity.com/paper/2409.06407/) (2024)
- [HS-SLAM: Hybrid Representation with Structural Supervision for Improved Dense SLAM](https://mlsanity.com/paper/2503.21778/) (2025)
- [SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting](https://mlsanity.com/paper/2507.15602/) (2025)
- [GrowSplat: Constructing Temporal Digital Twins of Plants with Gaussian Splats](https://mlsanity.com/paper/2505.10923/) (2025)
- [Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones](https://mlsanity.com/paper/2602.21101/) (2026)
- [RouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian Splatting](https://mlsanity.com/paper/2609.09606/) (2026)

## Abstract (arXiv)

For robotics applications where there is a limited number of (typically ego-centric) views, parametric representations such as neural radiance fields (NeRFs) generalize better than non-parametric ones such as Gaussian splatting (GS) to views that are very different from those in the training data; GS however can render much faster than NeRFs. We develop a procedure to convert back and forth between the two. Our approach achieves the best of both NeRFs (superior PSNR, SSIM, and LPIPS on dissimilar views, and a compact representation) and GS (real-time rendering and ability for easily modifying the representation); the computational cost of these conversions is minor compared to training the two from scratch.