3DGS$^3$: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering

TL;DR

3DGS$^3$ introduces a unified post-processing framework that enhances real-time 3D Gaussian Splatting rendering by jointly performing super sampling and frame interpolation, improving resolution and frame rate.

Contribution

It proposes Gradient-Aware Super Sampling and Lightweight Temporal Frame Interpolation modules to boost rendering quality and efficiency without altering the core 3DGS pipeline.

Findings

Achieves higher rendering efficiency and visual quality compared to state-of-the-art methods.

Demonstrates compatibility with existing 3DGS acceleration techniques.

Provides superior results on public datasets.

Abstract

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.