# AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field

arXiv: https://arxiv.org/abs/2405.12369 · HTML: https://mlsanity.com/paper/2405.12369/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 20 May 2024.

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

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [Editing Conditional Radiance Fields](https://mlsanity.com/paper/2105.06466/) (2021)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [CodeNeRF: Disentangled Neural Radiance Fields for Object Categories](https://mlsanity.com/paper/2109.01750/) (2021)
- [NASA: Neural Articulated Shape Approximation](https://mlsanity.com/paper/1912.03207/) (2019)
- [Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering](https://mlsanity.com/paper/2311.17089/) (2023)
- [GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering](https://mlsanity.com/paper/2402.10128/) (2024)
- [Object-Compositional Neural Implicit Surfaces](https://mlsanity.com/paper/2207.09686/) (2022)
- [NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations](https://mlsanity.com/paper/2207.10985/) (2022)
- [On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy](https://mlsanity.com/paper/2402.00752/) (2024)
- [TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2401.06003/) (2024)

## Built on by (most cited first, 18 of 18)

- [3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods](https://mlsanity.com/paper/2407.09510/) (2024)
- [Deformable Beta Splatting](https://mlsanity.com/paper/2501.18630/) (2025)
- [GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting](https://mlsanity.com/paper/2411.06019/) (2024)
- [Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS](https://mlsanity.com/paper/2506.09534/) (2025)
- [SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2501.07015/) (2025)
- [GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed Materials](https://mlsanity.com/paper/2601.09265/) (2026)
- [MEGS2: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning](https://mlsanity.com/paper/2509.07021/) (2025)
- [DHGS: Decoupled Hybrid Gaussian Splatting for Driving Scene](https://mlsanity.com/paper/2407.16600/) (2024)
- [FruitNinja: 3D Object Interior Texture Generation with Gaussian Splatting](https://mlsanity.com/paper/2411.12089/) (2024)
- [Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting](https://mlsanity.com/paper/2501.00625/) (2024)
- [ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction](https://mlsanity.com/paper/2509.03775/) (2025)
- [Enhancing 3D Gaussian Splatting Compression via Spatial Condition-based Prediction](https://mlsanity.com/paper/2503.23337/) (2025)
- [Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap](https://mlsanity.com/paper/2510.23494/) (2025)
- [MMGS: 10× Compressed 3DGS through Optimal Transport Aggregation based on Multi-view Ranking](https://mlsanity.com/paper/2605.19304/) (2026)
- [Structured-Li-GS: Structured 3D Gaussians Splatting with LiDAR Incorporation and Spatial Constraints](https://mlsanity.com/paper/2606.27509/) (2026)
- [IDU: Incremental Dynamic Update of Existing 3D Virtual Environments with New Imagery Data](https://mlsanity.com/paper/2508.17579/) (2025)
- [Direct Object-Level Reconstruction via Probabilistic Gaussian Splatting](https://mlsanity.com/paper/2603.14316/) (2026)
- [LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting](https://mlsanity.com/paper/2603.28431/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) has recently advanced radiance field reconstruction by offering superior capabilities for novel view synthesis and real-time rendering speed. However, its strategy of blending optimization and adaptive density control might lead to sub-optimal results; it can sometimes yield noisy geometry and blurry artifacts due to prioritizing optimizing large Gaussians at the cost of adequately densifying smaller ones. To address this, we introduce AtomGS, consisting of Atomized Proliferation and Geometry-Guided Optimization. The Atomized Proliferation constrains ellipsoid Gaussians of various sizes into more uniform-sized Atom Gaussians. The strategy enhances the representation of areas with fine features by placing greater emphasis on densification in accordance with scene details. In addition, we proposed a Geometry-Guided Optimization approach that incorporates an Edge-Aware Normal Loss. This optimization method effectively smooths flat surfaces while preserving intricate details. Our evaluation shows that AtomGS outperforms existing state-of-the-art methods in rendering quality. Additionally, it achieves competitive accuracy in geometry reconstruction and offers a significant improvement in training speed over other SDF-based methods. More interactive demos can be found in our website (https://rongliu-leo.github.io/AtomGS/).