# GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction

arXiv: https://arxiv.org/abs/2509.25075 · HTML: https://mlsanity.com/paper/2509.25075/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 40 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [3D Gaussian as a New Era: A Survey](https://mlsanity.com/paper/2402.07181/) (2024)
- [R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction](https://mlsanity.com/paper/2405.20693/) (2024)
- [X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction](https://mlsanity.com/paper/2503.21779/) (2025)
- [CryoFormer: Continuous Heterogeneous Cryo-EM Reconstruction using Transformer-based Neural Representations](https://mlsanity.com/paper/2303.16254/) (2023)

## Built on by (most cited first, 3 of 3)

- [GR-Diffusion: 3D Gaussian Representation Meets Diffusion in Whole-Body PET Reconstruction](https://mlsanity.com/paper/2602.11653/) (2026)
- [3D Gaussian Splatting for Annular Dark Field Scanning Transmission Electron Microscopy Tomography Reconstruction](https://mlsanity.com/paper/2604.04693/) (2026)
- [NanoMorph-3D: An End-to-End Physics-Driven Unrolling Framework for Nanomaterial Reconstruction](https://mlsanity.com/paper/2608.03257/) (2026)

## Abstract (arXiv)

Cryo-electron microscopy (cryo-EM) has become a central tool for high-resolution structural biology, yet the massive scale of datasets (often exceeding 100k particle images) renders 3D reconstruction both computationally expensive and memory intensive. Traditional Fourier-space methods are efficient but lose fidelity due to repeated transforms, while recent real-space approaches based on neural radiance fields (NeRFs) improve accuracy but incur cubic memory and computation overhead. Therefore, we introduce GEM, a novel cryo-EM reconstruction framework built on 3D Gaussian Splatting (3DGS) that operates directly in real-space while maintaining high efficiency. Instead of modeling the entire density volume, GEM represents proteins with compact 3D Gaussians, each parameterized by only 11 values. To further improve the training efficiency, we designed a novel gradient computation to 3D Gaussians that contribute to each voxel. This design substantially reduced both memory footprint and training cost. On standard cryo-EM benchmarks, GEM achieves up to 48% faster training and 12% lower memory usage compared to state-of-the-art methods, while improving local resolution by as much as 38.8%. These results establish GEM as a practical and scalable paradigm for cryo-EM reconstruction, unifying speed, efficiency, and high-resolution accuracy. Our code is available at https://github.com/UNITES-Lab/GEM.