# EntON: Eigenentropy-Optimized Neighborhood Densification in 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2603.06216 · HTML: https://mlsanity.com/paper/2603.06216/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (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)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://mlsanity.com/paper/2406.06521/) (2024)
- [Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes](https://mlsanity.com/paper/2404.10772/) (2024)
- [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024)
- [Taming 3DGS: High-Quality Radiance Fields with Limited Resources](https://mlsanity.com/paper/2406.15643/) (2024)
- [High-quality Surface Reconstruction using Gaussian Surfels](https://mlsanity.com/paper/2404.17774/) (2024)
- [FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization](https://mlsanity.com/paper/2403.06908/) (2024)
- [Triangle Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2505.19175/) (2025)
- [Faster-GS: Analyzing and Improving Gaussian Splatting Optimization](https://mlsanity.com/paper/2602.09999/) (2026)
- [GSCodec Studio: A Modular Framework for Gaussian Splat Compression](https://mlsanity.com/paper/2506.01822/) (2025)
- [AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting](https://mlsanity.com/paper/2509.11003/) (2025)
- [UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction](https://mlsanity.com/paper/2412.03473/) (2024)
- [Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting](https://mlsanity.com/paper/2508.02493/) (2025)
- [GS4Buildings: Prior-Guided Gaussian Splatting for 3D Building Reconstruction](https://mlsanity.com/paper/2508.07355/) (2025)
- [3D Density-Gradient based Edge Detection on Neural Radiance Fields (NeRFs) for Geometric Reconstruction](https://mlsanity.com/paper/2309.14800/) (2023)
- [ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction](https://mlsanity.com/paper/2601.06997/) (2026)

## Abstract (arXiv)

We present a novel Eigenentropy-optimized neighboorhood densification strategy EntON in 3D Gaussian Splatting (3DGS) for geometrically accurate and high-quality rendered 3D reconstruction. While standard 3DGS produces Gaussians whose centers and surfaces are poorly aligned with the underlying object geometry, surface-focused reconstruction methods frequently sacrifice photometric accuracy. In contrast to the conventional densification strategy, which relies on the magnitude of the view-space position gradient, our approach introduces a geometry-aware strategy to guide adaptive splitting and pruning. Specifically, we compute the 3D shape feature Eigenentropy from the eigenvalues of the covariance matrix in the k-nearest neighborhood of each Gaussian center, which quantifies the local structural order. These Eigenentropy values are integrated into an alternating optimization framework: During the optimization process, the algorithm alternates between (i) standard gradient-based densification, which refines regions via view-space gradients, and (ii) Eigenentropy-aware densification, which preferentially densifies Gaussians in low-Eigenentropy (ordered, flat) neighborhoods to better capture fine geometric details on the object surface, and prunes those in high-Eigenentropy (disordered, spherical) regions. We provide quantitative and qualitative evaluations on two benchmark datasets: small-scale DTU dataset and large-scale TUM2TWIN dataset, covering man-made objects and urban scenes. Experiments demonstrate that our Eigenentropy-aware alternating densification strategy improves geometric accuracy by up to 33% and rendering quality by up to 7%, while reducing the number of Gaussians by up to 50% and training time by up to 23%. Overall, EnTON achieves a favorable balance between geometric accuracy, rendering quality and efficiency by avoiding unnecessary scene expansion.