# GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control

arXiv: https://arxiv.org/abs/2507.00363 · HTML: https://mlsanity.com/paper/2507.00363/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 57 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [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)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering](https://mlsanity.com/paper/2311.17089/) (2023)
- [Cognitive Memory in Large Language Models](https://mlsanity.com/paper/2504.02441/) (2025)
- [GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs](https://mlsanity.com/paper/2505.17653/) (2025)
- [Continual Learning for Image Segmentation with Dynamic Query](https://mlsanity.com/paper/2311.17450/) (2023)
- [DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models](https://mlsanity.com/paper/2503.11265/) (2025)
- [GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Models](https://mlsanity.com/paper/2506.01277/) (2025)
- [LLM-CoT Enhanced Graph Neural Recommendation with Harmonized Group Policy Optimization](https://mlsanity.com/paper/2505.12396/) (2025)
- [End-to-end Remote Sensing Change Detection of Unregistered Bi-temporal Images for Natural Disasters](https://mlsanity.com/paper/2307.15128/) (2023)
- [Boosting General Trimap-free Matting in the Real-World Image](https://mlsanity.com/paper/2405.17916/) (2024)
- [Edge-guided and Class-balanced Active Learning for Semantic Segmentation of Aerial Images](https://mlsanity.com/paper/2405.18078/) (2024)
- [F2Net: A Frequency-Fused Network for Ultra-High Resolution Remote Sensing Segmentation](https://mlsanity.com/paper/2506.07847/) (2025)
- [The Binary Quantized Neural Network for Dense Prediction via Specially Designed Upsampling and Attention](https://mlsanity.com/paper/2405.17776/) (2024)
- [Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation](https://mlsanity.com/paper/2405.19568/) (2024)
- [Synthetic Lung X-ray Generation through Cross-Attention and Affinity Transformation](https://mlsanity.com/paper/2503.07209/) (2025)
- [GMM-Based Comprehensive Feature Extraction and Relative Distance Preservation For Few-Shot Cross-Modal Retrieval](https://mlsanity.com/paper/2505.13306/) (2025)

## Built on by (most cited first, 2 of 2)

- [The Role of Initialization in 3D Gaussian Splatting](https://mlsanity.com/paper/2603.20714/) (2026)
- [MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning](https://mlsanity.com/paper/2607.24424/) (2026)

## Abstract (arXiv)

We propose a method to enhance 3D Gaussian Splatting (3DGS)~citeKerbl2023, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting real-time performance, and it has gained popularity due to its explicit 3D Gaussian representation. However, 3DGS heavily depends on accurate initialization and faces difficulties in optimizing unstructured Gaussian distributions into ordered surfaces, with limited adaptive density control mechanism proposed so far. Our first key contribution is a geometry-guided initialization to predict Gaussian parameters, ensuring precise placement and faster convergence. We then introduce a surface-aligned optimization strategy to refine Gaussian placement, improving geometric accuracy and aligning with the surface normals of the scene. Finally, we present a dynamic adaptive density control mechanism that adjusts Gaussian density based on regional complexity, for visual fidelity. These innovations enable our method to achieve high-fidelity real-time rendering and significant improvements in visual quality, even in complex scenes. Our method demonstrates comparable or superior results to state-of-the-art methods, rendering high-fidelity images in real time.