# EdgeGaussians -- 3D Edge Mapping via Gaussian Splatting

arXiv: https://arxiv.org/abs/2409.12886 · HTML: https://mlsanity.com/paper/2409.12886/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 104 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Builds on (most cited first, 30 of 34)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [EC-Net: an Edge-aware Point set Consolidation Network](https://mlsanity.com/paper/1807.06010/) (2018)
- [Line Segment Detection Using Transformers without Edges](https://mlsanity.com/paper/2101.01909/) (2021)
- [PIE-NET: Parametric Inference of Point Cloud Edges](https://mlsanity.com/paper/2007.04883/) (2020)
- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022)
- [GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians](https://mlsanity.com/paper/2402.10483/) (2024)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [Learning to Reconstruct 3D Manhattan Wireframes from a Single Image](https://mlsanity.com/paper/1905.07482/) (2019)
- [PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds](https://mlsanity.com/paper/2103.02766/) (2021)
- [TP-LSD: Tri-Points Based Line Segment Detector](https://mlsanity.com/paper/2009.05505/) (2020)
- [Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning](https://mlsanity.com/paper/2210.12971/) (2022)
- [Fast Resampling of 3D Point Clouds via Graphs](https://mlsanity.com/paper/1702.06397/) (2017)
- [NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images](https://mlsanity.com/paper/2303.07653/) (2023)
- [NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud](https://mlsanity.com/paper/2303.16465/) (2023)
- [PCEDNet : A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds](https://mlsanity.com/paper/2011.01630/) (2020)
- [Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Welding](https://mlsanity.com/paper/1809.10468/) (2018)
- [SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes](https://mlsanity.com/paper/2304.06531/) (2023)
- [Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment](https://mlsanity.com/paper/2012.08228/) (2020)
- [HoW-3D: Holistic 3D Wireframe Perception from a Single Image](https://mlsanity.com/paper/2208.06999/) (2022)
- [NEAT: Distilling 3D Wireframes from Neural Attraction Fields](https://mlsanity.com/paper/2307.10206/) (2023)
- [3D Neural Edge Reconstruction](https://mlsanity.com/paper/2405.19295/) (2024)
- [LCD -- Line Clustering and Description for Place Recognition](https://mlsanity.com/paper/2010.10867/) (2020)
- [Image-Based Place Recognition on Bucolic Environment Across Seasons From Semantic Edge Description](https://mlsanity.com/paper/1910.12468/) (2019)

## Built on by (most cited first, 10 of 10)

- [Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction](https://mlsanity.com/paper/2506.21401/) (2025)
- [SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splatting](https://mlsanity.com/paper/2503.14786/) (2025)
- [ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis](https://mlsanity.com/paper/2505.19492/) (2025)
- [LineGS : 3D Line Segment Representation on 3D Gaussian Splatting](https://mlsanity.com/paper/2412.00477/) (2024)
- [Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representation](https://mlsanity.com/paper/2601.05394/) (2026)
- [3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience](https://mlsanity.com/paper/2604.08042/) (2026)
- [SF-Recon: Simplification-Free Lightweight Building Reconstruction via 3D Gaussian Splatting](https://mlsanity.com/paper/2511.13278/) (2025)
- [FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing](https://mlsanity.com/paper/2605.09362/) (2026)
- [LEGS: Laplacian-Enhanced Gaussian Splatting with a Nonlinear Weighted Loss](https://mlsanity.com/paper/2606.07932/) (2026)
- [CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction](https://mlsanity.com/paper/2609.14521/) (2026)

## Abstract (arXiv)

With their meaningful geometry and their omnipresence in the 3D world, edges are extremely useful primitives in computer vision. 3D edges comprise of lines and curves, and methods to reconstruct them use either multi-view images or point clouds as input. State-of-the-art image-based methods first learn a 3D edge point cloud then fit 3D edges to it. The edge point cloud is obtained by learning a 3D neural implicit edge field from which the 3D edge points are sampled on a specific level set (0 or 1). However, such methods present two important drawbacks: i) it is not realistic to sample points on exact level sets due to float imprecision and training inaccuracies. Instead, they are sampled within a range of levels so the points do not lie accurately on the 3D edges and require further processing. ii) Such implicit representations are computationally expensive and require long training times. In this paper, we address these two limitations and propose a 3D edge mapping that is simpler, more efficient, and preserves accuracy. Our method learns explicitly the 3D edge points and their edge direction hence bypassing the need for point sampling. It casts a 3D edge point as the center of a 3D Gaussian and the edge direction as the principal axis of the Gaussian. Such a representation has the advantage of being not only geometrically meaningful but also compatible with the efficient training optimization defined in Gaussian Splatting. Results show that the proposed method produces edges as accurate and complete as the state-of-the-art while being an order of magnitude faster. Code is released at https://github.com/kunalchelani/EdgeGaussians.