Efficient 3D Gaussian splatting improves real time scene rendering quality
EffGS: Efficient and High-Fidelity Gaussian Splatting
Computer Vision and Pattern Recognition
Summary
Rendering 3D scenes quickly and in high detail is important for things like virtual reality or video games. The existing method called 3D Gaussian Splatting can do this in real time but struggles with big, complex scenes without losing quality. The authors propose EffGS, which speeds up training and rendering by smarter ways of focusing detail where it matters and adjusting the size of visual primitives. This approach keeps the rendered scenes looking good even for large-scale environments while being more efficient.
What this means in practice
- •For virtual reality developers: Create more detailed and realistic VR scenes that render in real time without sacrificing quality on large environments.
- •For game engine programmers: Improve training and rendering speed in engines for better performance and visual fidelity in complex game levels.
Authors
Changbai Li, Shuo Yang, Yichen Yang, Shuwei Shao, Huobin Tan
Abstract
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but existing general-purpose acceleration methods suffer severe rendering quality degradation when extended to more complex, large-scale scenes. To address this issue, we propose EffGS, a more general acceleration framework that improves training and rendering efficiency while maintaining reconstruction quality comparable to or better than vanilla 3DGS across bounded and large-scale scenes. EffGS combines frequency-aware guidance, localized density control, and adaptive primitive scale modulation. First, an importance scoring mechanism combines pixel-wise reconstruction errors with a difference-of-Gaussians mask scheduled over training to provide stage-dependent spatial guidance. Second, localized densification and pruning restricts density modifications to Gaussians with valid projected footprints in the sampled views. Third, learnable per-Gaussian scale modulation adjusts effective primitive extent during optimization while retaining the Compact Box rasterization rule. Extensive experiments on bounded and large-scale scene datasets demonstrate a favorable balance between reconstruction quality, training time, and primitive count. Component ablations and matched-primitive-budget comparisons further support the effectiveness of the framework.