EdgeGaussians - 3D Edge Mapping via Gaussian Splatting

Paper in proceeding, 2025

With their meaningful geometry and omnipresence in the 3D world, edges are extremely useful primitives in computer vision. Methods for 3D edge reconstruction have 1) either focused on reconstructing 3D edges by triangulating tracks of 2D line segments across images or 2) more recently, learning a 3D edge distance field from multi-view images. The triangulation-based methods struggle to repeatedly detect and robustly match line segments resulting in noisy and incomplete reconstructions in many cases. Methods in the latter class rely on sampling edge points from the learnt implicit field, which is limited by the spatial resolution of the voxel grid used for sampling, resulting in imprecise points that require refinement. Further, such methods require a long training that scales poorly with the size of the scene. In this paper, we propose a method that explicitly learns 3D edge points with a 3D Gaussian Splatting representation trained from edge images. The 3D Gaussians are regularized to have their directions of largest variance along the edge they lie on, enabling clustering into separate edges. Backed by efficient training, the proposed method produces results better than or at-par with the current state-of-the-art methods, while being an order of magnitude faster. Code released at https://github.com/kunalchelani/EdgeGaussians.