Pushing Rendering Boundaries: Hard Gaussian Splatting

TL;DR

This paper introduces Hard Gaussian Splatting (HGS), a novel method that improves 3D view synthesis by growing hard Gaussians based on significant multi-view gradients and rendering errors, reducing artifacts and enhancing quality.

Contribution

The paper proposes Hard Gaussian Splatting, which considers multi-view gradients and errors to grow Gaussians, addressing limitations of classical methods and achieving superior rendering results.

Findings

Achieves state-of-the-art rendering quality.

Maintains real-time efficiency.

Reduces artifacts like blurring and needle-like distortions.

Abstract

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to reduce rendering loss. However, this average operation smooths the positional gradients from different viewpoints and rendering errors from different pixels, hindering the growth and optimization of many defective Gaussians. This leads to strong spurious artifacts in some areas. To address this problem, we propose Hard Gaussian Splatting, dubbed HGS, which considers multi-view significant positional gradients and rendering errors to grow hard Gaussians that fill the gaps of classical Gaussian Splatting on 3D scenes, thus achieving superior NVS results. In detail, we present positional gradient driven HGS, which leverages multi-view significant positional gradients to uncover hard Gaussians. Moreover, we propose rendering error guided HGS, which identifies noticeable pixel rendering errors and potentially over-large Gaussians to jointly mine hard Gaussians. By growing and optimizing these hard Gaussians, our method helps to resolve blurring and needle-like artifacts. Experiments on various datasets demonstrate that our method achieves state-of-the-art rendering quality while maintaining real-time efficiency.