# Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2403.09413 · HTML: https://mlsanity.com/paper/2403.09413/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 30 of 33)

- [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)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization](https://mlsanity.com/paper/2303.07418/) (2023)
- [GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models](https://mlsanity.com/paper/2310.08529/) (2023)
- [NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior](https://mlsanity.com/paper/2212.07388/) (2022)
- [DynIBaR: Neural Dynamic Image-Based Rendering](https://mlsanity.com/paper/2211.11082/) (2022)
- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [Vision-Only Robot Navigation in a Neural Radiance World](https://mlsanity.com/paper/2110.00168/) (2021)
- [Learning to Render Novel Views from Wide-Baseline Stereo Pairs](https://mlsanity.com/paper/2304.08463/) (2023)
- [Accelerated Hierarchical Density Clustering](https://mlsanity.com/paper/1705.07321/) (2017)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [VR-NeRF: High-Fidelity Virtualized Walkable Spaces](https://mlsanity.com/paper/2311.02542/) (2023)
- [GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency](https://mlsanity.com/paper/2301.10941/) (2023)

## Built on by (most cited first, 30 of 34)

- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering](https://mlsanity.com/paper/2406.02518/) (2024)
- [C3G: Learning Compact 3D Representations with 2K Gaussians](https://mlsanity.com/paper/2512.04021/) (2025)
- [Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction](https://mlsanity.com/paper/2412.06234/) (2024)
- [HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images](https://mlsanity.com/paper/2407.16503/) (2024)
- [NeRF Is a Valuable Assistant for 3D Gaussian Splatting](https://mlsanity.com/paper/2507.23374/) (2025)
- [DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior](https://mlsanity.com/paper/2502.09111/) (2025)
- [HyperGS: Hyperspectral 3D Gaussian Splatting](https://mlsanity.com/paper/2412.12849/) (2024)
- [Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views](https://mlsanity.com/paper/2503.24382/) (2025)
- [RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS](https://mlsanity.com/paper/2506.02751/) (2025)
- [Elite-EvGS: Learning Event-based 3D Gaussian Splatting by Distilling Event-to-Video Priors](https://mlsanity.com/paper/2409.13392/) (2024)
- [Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding](https://mlsanity.com/paper/2512.17817/) (2025)
- [Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields](https://mlsanity.com/paper/2412.13547/) (2024)
- [GaussianVideo: Efficient Video Representation and Compression by Gaussian Splatting](https://mlsanity.com/paper/2503.04333/) (2025)
- [PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage](https://mlsanity.com/paper/2508.02443/) (2025)
- [Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering](https://mlsanity.com/paper/2410.04646/) (2024)
- [Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting](https://mlsanity.com/paper/2508.02493/) (2025)
- [Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting](https://mlsanity.com/paper/2602.20933/) (2026)
- [Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting](https://mlsanity.com/paper/2501.14534/) (2025)
- [OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects](https://mlsanity.com/paper/2510.20605/) (2025)
- [Enhancement of 3D Gaussian Splatting using Raw Mesh for Photorealistic Recreation of Architectures](https://mlsanity.com/paper/2407.15435/) (2024)
- [MoRe-3DGSMR: Motion-resolved reconstruction framework for free-breathing pulmonary MRI based on 3D Gaussian representation](https://mlsanity.com/paper/2505.04959/) (2025)
- [ES-Gaussian: Gaussian Splatting Mapping via Error Space-Based Gaussian Completion](https://mlsanity.com/paper/2410.06613/) (2024)
- [FlameGS: Reconstruct flame light field via Gaussian Splatting](https://mlsanity.com/paper/2412.19841/) (2024)
- [Reconstructing Tornadoes in 3D with Gaussian Splatting](https://mlsanity.com/paper/2506.18677/) (2025)
- [TreeDGS: Aerial Gaussian Splatting for Distant DBH Measurement](https://mlsanity.com/paper/2601.12823/) (2026)
- [A Step to Decouple Optimization in 3DGS](https://mlsanity.com/paper/2601.16736/) (2026)
- [The Role of Initialization in 3D Gaussian Splatting](https://mlsanity.com/paper/2603.20714/) (2026)
- [GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition](https://mlsanity.com/paper/2607.21416/) (2026)

## Abstract (arXiv)

3D Gaussian splatting (3DGS) has recently demonstrated impressive capabilities in real-time novel view synthesis and 3D reconstruction. However, 3DGS heavily depends on the accurate initialization derived from Structure-from-Motion (SfM) methods. When the quality of the initial point cloud deteriorates, such as in the presence of noise or when using randomly initialized point cloud, 3DGS often undergoes large performance drops. To address this limitation, we propose a novel optimization strategy dubbed RAIN-GS (Relaing Accurate Initialization Constraint for 3D Gaussian Splatting). Our approach is based on an in-depth analysis of the original 3DGS optimization scheme and the analysis of the SfM initialization in the frequency domain. Leveraging simple modifications based on our analyses, RAIN-GS successfully trains 3D Gaussians from sub-optimal point cloud (e.g., randomly initialized point cloud), effectively relaxing the need for accurate initialization. We demonstrate the efficacy of our strategy through quantitative and qualitative comparisons on multiple datasets, where RAIN-GS trained with random point cloud achieves performance on-par with or even better than 3DGS trained with accurate SfM point cloud. Our project page and code can be found at https://ku-cvlab.github.io/RAIN-GS.