3D Gaussian Splatting (3DGS) enables high-quality real-time 3D rendering but faces challenges in efficiently scaling to ultra-dense scenes and high-resolution due to computational bottlenecks that limit its use in latency-sensitive applications. Instead of optimizing the splatting pipeline itself, we propose \textbf{3DGS$^3$}, a unified post-rendering framework that jointly performs super sampling and frame interpolation through differentiable processing of low-resolution outputs to achieve both high-resolution and high-frame-rate rendering. Our \textbf{Gradient\- \-Aware Super Sampling (GASS)} module leverages the continuous differentiability of 3DGS to extract image gradients that guide a GRU-based refinement network to enable high-fidelity super sampling. Furthermore, a \textbf{Lightweight Temporal Frame Interpolation (LTFI)} module based on a compact U-Net-like backbone fuses temporal and differentiable spatial cues from consecutive frames to synthesize temporally coherent intermediate frames. Experiments on public datasets demonstrate that 3DGS$^3$ achieves superior rendering efficiency and visual quality when compared with state-of-the-art methods and remains compatible with existing 3DGS acceleration techniques. The code will be publicly released upon acceptance.

翻译：3D高斯泼溅（3DGS）实现了高质量实时3D渲染，但由于计算瓶颈限制了其在延迟敏感型应用中的使用，在超密集场景和高分辨率场景下存在高效扩展难题。本文不直接优化泼溅管线本身，而是提出**3DGS$^3$**，一种统一的后渲染框架，通过对低分辨率输出进行可微处理，联合执行超级采样与帧插值，从而实现高分辨率与高帧率渲染。我们的**梯度感知超级采样（GASS）**模块利用3DGS的连续可微性提取图像梯度，引导基于GRU的精修网络实现高保真超级采样。此外，**轻量级时序帧插值（LTFI）**模块基于紧凑型U-Net类骨干网络，融合连续帧的时序信息与可微空间线索，以合成时序连贯的中间帧。在公开数据集上的实验表明，与现有最优方法相比，3DGS$^3$在渲染效率和视觉质量上均表现优异，且与现有3DGS加速技术保持兼容。相关代码将在论文接收后公开发布。