# RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians

arXiv: https://arxiv.org/abs/2406.11836 · HTML: https://mlsanity.com/paper/2406.11836/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [One weird trick for parallelizing convolutional neural networks](https://mlsanity.com/paper/1404.5997/) (2014)
- [BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering](https://mlsanity.com/paper/2112.05504/) (2021)
- [BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis](https://mlsanity.com/paper/2302.14859/) (2023)
- [MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes](https://mlsanity.com/paper/2302.12249/) (2023)
- [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024)
- [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023)
- [Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement](https://mlsanity.com/paper/2303.02091/) (2023)
- [Grid-guided Neural Radiance Fields for Large Urban Scenes](https://mlsanity.com/paper/2303.14001/) (2023)
- [Compressing Volumetric Radiance Fields to 1 MB](https://mlsanity.com/paper/2211.16386/) (2022)
- [Masked Wavelet Representation for Compact Neural Radiance Fields](https://mlsanity.com/paper/2212.09069/) (2022)
- [Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Features](https://mlsanity.com/paper/2303.03003/) (2023)
- [Towards Good Practices for Very Deep Two-Stream ConvNets](https://mlsanity.com/paper/1507.02159/) (2015)

## Built on by (most cited first, 16 of 16)

- [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024)
- [Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes](https://mlsanity.com/paper/2412.01745/) (2024)
- [Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstruction](https://mlsanity.com/paper/2412.04887/) (2024)
- [Balanced 3DGS: Gaussian-wise Parallelism Rendering with Fine-Grained Tiling](https://mlsanity.com/paper/2412.17378/) (2024)
- [FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting](https://mlsanity.com/paper/2507.06671/) (2025)
- [GS-Scale: Unlocking Large-Scale 3D Gaussian Splatting Training via Host Offloading](https://mlsanity.com/paper/2509.15645/) (2025)
- [Gaussian On-the-Fly Splatting: A Progressive Framework for Robust Near Real-Time 3DGS Optimization](https://mlsanity.com/paper/2503.13086/) (2025)
- [Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting](https://mlsanity.com/paper/2505.23280/) (2025)
- [CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting](https://mlsanity.com/paper/2511.04951/) (2025)
- [A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memory](https://mlsanity.com/paper/2507.01110/) (2025)
- [BlitzGS: City-Scale Gaussian Splatting at Lightning Speed](https://mlsanity.com/paper/2605.13794/) (2026)
- [TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization](https://mlsanity.com/paper/2605.20150/) (2026)
- [HiGS: A Hierarchical Rendering Architecture for Real-Time 3D Gaussian Splatting](https://mlsanity.com/paper/2606.00352/) (2026)
- [A-TDOM: Active TDOM via On-the-Fly 3DGS](https://mlsanity.com/paper/2509.12759/) (2025)
- [LandMarkSystem Technical Report](https://mlsanity.com/paper/2503.21364/) (2025)
- [TemporalGS: Training-Free Plug-and-Play Acceleration for 3D Gaussian Splatting Rendering via Temporal Priors](https://mlsanity.com/paper/2607.03390/) (2026)

## Abstract (arXiv)

In this work, we explore the possibility of training high-parameter 3D Gaussian splatting (3DGS) models on large-scale, high-resolution datasets. We design a general model parallel training method for 3DGS, named RetinaGS, which uses a proper rendering equation and can be applied to any scene and arbitrary distribution of Gaussian primitives. It enables us to explore the scaling behavior of 3DGS in terms of primitive numbers and training resolutions that were difficult to explore before and surpass previous state-of-the-art reconstruction quality. We observe a clear positive trend of increasing visual quality when increasing primitive numbers with our method. We also demonstrate the first attempt at training a 3DGS model with more than one billion primitives on the full MatrixCity dataset that attains a promising visual quality.