Lightweight Gradient-Aware Upscaling of 3D Gaussian Splatting Images

We introduce an image upscaling technique tailored for 3D Gaussian Splatting (3DGS) on lightweight GPUs. Compared to 3DGS, it achieves significantly higher rendering speeds and reduces commonly observed reconstruction artifacts. Our technique upscales low-resolution 3DGS renderings with a marginal increase in cost by directly leveraging the analytical image gradients of Gaussians for gradientbased bicubic spline interpolation. The technique is agnostic to the specific 3DGS implementation, achieving novel view synthesis at rates $3 \times-4 \times$ higher than the baseline implementation. Through extensive experiments on multiple datasets, we showcase the performance improvements and high reconstruction fidelity attainable with gradient-aware upscaling of 3DGS images. We further demonstrate the integration of gradient-aware upscaling into the gradientbased optimization of a 3DGS model and analyze its effects on reconstruction quality and performance.