Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting

TL;DR

Pixel-GS enhances 3D Gaussian Splatting by incorporating pixel coverage into the growth condition, improving reconstruction quality and detail, especially in areas with sparse initial points, while maintaining real-time rendering performance.

Contribution

It introduces a pixel-aware gradient control method for 3D Gaussian Splatting, addressing growth issues of large Gaussians and improving reconstruction accuracy.

Findings

Achieves state-of-the-art rendering quality on challenging datasets.

Maintains real-time rendering speed.

Effectively grows points in areas with insufficient initial data.

Abstract

3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results while advancing real-time rendering performance. However, it relies heavily on the quality of the initial point cloud, resulting in blurring and needle-like artifacts in areas with insufficient initializing points. This is mainly attributed to the point cloud growth condition in 3DGS that only considers the average gradient magnitude of points from observable views, thereby failing to grow for large Gaussians that are observable for many viewpoints while many of them are only covered in the boundaries. To this end, we propose a novel method, named Pixel-GS, to take into account the number of pixels covered by the Gaussian in each view during the computation of the growth condition. We regard the covered pixel numbers as the weights to dynamically average the gradients from different views, such that the growth of large Gaussians can be prompted. As a result, points within the areas with insufficient initializing points can be grown more effectively, leading to a more accurate and detailed reconstruction. In addition, we propose a simple yet effective strategy to scale the gradient field according to the distance to the camera, to suppress the growth of floaters near the camera. Extensive experiments both qualitatively and quantitatively demonstrate that our method achieves state-of-the-art rendering quality while maintaining real-time rendering speed, on the challenging Mip-NeRF 360 and Tanks & Temples datasets.