# EGGS: Edge Guided Gaussian Splatting for Radiance Fields

arXiv: https://arxiv.org/abs/2404.09105 · HTML: https://mlsanity.com/paper/2404.09105/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 51 references that are in the map.
- First posted on arXiv 14 Apr 2024.

## Builds on (most cited first, 16 of 16)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [GaussianPro: 3D Gaussian Splatting with Progressive Propagation](https://mlsanity.com/paper/2402.14650/) (2024)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Gaussian Shell Maps for Efficient 3D Human Generation](https://mlsanity.com/paper/2311.17857/) (2023)
- [GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation](https://mlsanity.com/paper/2312.01632/) (2023)
- [Side Window Filtering](https://mlsanity.com/paper/1905.07177/) (2019)
- [Weighted Mean Curvature](https://mlsanity.com/paper/1903.07189/) (2019)
- [Fast and High-Quality Blind Multi-Spectral Image Pansharpening](https://mlsanity.com/paper/2103.09943/) (2021)
- [A Discrete Scheme for Computing Image's Weighted Gaussian Curvature](https://mlsanity.com/paper/2101.07927/) (2021)
- [Quarter Laplacian Filter for Edge Aware Image Processing](https://mlsanity.com/paper/2101.07933/) (2021)
- [Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2403.14244/) (2024)

## Built on by (most cited first, 9 of 9)

- [DisC-GS: Discontinuity-aware Gaussian Splatting](https://mlsanity.com/paper/2405.15196/) (2024)
- [Aquatic-GS: A Hybrid 3D Representation for Underwater Scenes](https://mlsanity.com/paper/2411.00239/) (2024)
- [DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions](https://mlsanity.com/paper/2501.12369/) (2025)
- [Drop-In Perceptual Optimization for 3D Gaussian Splatting](https://mlsanity.com/paper/2603.23297/) (2026)
- [Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction](https://mlsanity.com/paper/2604.23551/) (2026)
- [SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting](https://mlsanity.com/paper/2512.03010/) (2025)
- [GDGS: Gradient Domain Gaussian Splatting for Sparse Representation of Radiance Fields](https://mlsanity.com/paper/2405.05446/) (2024)
- [Shared-kernel Wavelet Neural Networks for Poisson Image Reconstruction](https://mlsanity.com/paper/2604.24000/) (2026)
- [LEGS: Laplacian-Enhanced Gaussian Splatting with a Nonlinear Weighted Loss](https://mlsanity.com/paper/2606.07932/) (2026)

## Abstract (arXiv)

The Gaussian splatting methods are getting popular. However, their loss function only contains the ℓ1 norm and the structural similarity between the rendered and input images, without considering the edges in these images. It is well-known that the edges in an image provide important information. Therefore, in this paper, we propose an Edge Guided Gaussian Splatting (EGGS) method that leverages the edges in the input images. More specifically, we give the edge region a higher weight than the flat region. With such edge guidance, the resulting Gaussian particles focus more on the edges instead of the flat regions. Moreover, such edge guidance does not crease the computation cost during the training and rendering stage. The experiments confirm that such simple edge-weighted loss function indeed improves about 1~2 dB on several difference data sets. With simply plugging in the edge guidance, the proposed method can improve all Gaussian splatting methods in different scenarios, such as human head modeling, building 3D reconstruction, etc.