EGGS: Edge Guided Gaussian Splatting for Radiance Fields
Yuanhao Gong · 2024
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 yet effective edge-weighted loss function indeed improves about 1 ∼ 2 dB on several data sets. With simply using the edge guidance, the proposed method can improve all Gaussian splatting methods in different scenarios, such as human head modeling, 3D building reconstruction, WebGL, etc.