Uncertainty-aware 3D Edge Reconstruction with Difference of Gaussians

Caixia Zhou, Jiahao Ma, Yaping Huang, Haibin Ling, Jing Zhang

Keywords: Difference of Gaussians, Uncertainty, 3D Edge Reconstruction

Abstract: 3D edge reconstruction from posed multi-view images remains a critical yet under-explored task. While 3D Gaussian Splatting (3DGS)-based methods have recently achieved promising performance, they face two main challenges. First, edges exhibit clear discontinuities from the background, but the intrinsic smoothness of Gaussian kernels makes it challenging to model such discontinuities. Second, due to the absence of multi-view edge annotations, models are trained with pseudo labels instead. These pseudo labels extracted by pre-trained 2D edge detectors often exhibit cross-view inconsistencies, leading to degraded performance. To address these issues, we propose a novel uncertainty-aware 3D edge reconstruction using Difference of Gaussians (DoG) as kernels, called **EdgeDoG**. First, we incorporate DoG kernels to model edge discontinuities explicitly. Second, we design a dual-uncertainty strategy: *primitive-level* uncertainty is estimated via multi-view Fisher information to eliminate noisy 3D primitives, while *pixel-level* uncertainty is computed from gradients of rendered depth maps to reweight the training loss, thereby compensating for inconsistent 2D pseudo labels with robust 3D geometric cues. Extensive experiments on diverse datasets demonstrate that our method achieves superior performance compared to previous approaches.

Submission Number: 50