Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists

TL;DR

This work proposes novel training strategies and losses to shorten each Gaussian list used to render a pixel, which speeds up the splatting by involving fewer Gaussians along a ray and integrates the method into a rendering resolution scheduler which further improves efficiency through progressive resolution increase.

Abstract

3D Gaussian splatting (3DGS) has become a vital tool for learning a radiance field from multiple posed images. Although 3DGS shows great advantages over NeRF in terms of rendering quality and efficiency, it remains a research challenge to further improve the efficiency of learning 3D Gaussians. To overcome this challenge, we propose novel training strategies and losses to shorten each Gaussian list used to render a pixel, which speeds up the splatting by involving fewer Gaussians along a ray. Specifically, we shrink the size of each Gaussian by resetting their scales regularly, encouraging smaller Gaussians to cover fewer nearby pixels, which shortens the Gaussian lists of pixels. Additionally, we introduce an entropy constraint on the alpha blending procedure to sharpen the weight distribution of Gaussians along each ray, which drives dominant weights larger while making minor weights smaller. As a result, each Gaussian becomes more focused on the pixels where it is dominant, which reduces its impact on nearby pixels, leading to even shorter Gaussian lists. Eventually, we integrate our method into a rendering resolution scheduler which further improves efficiency through progressive resolution increase. We evaluate our method by comparing it with state-of-the-art methods on widely used benchmarks. Our results show significant advantages over others in efficiency without sacrificing rendering quality.

Figures (25)

• Figure 1: Heatmaps of per-tile Gaussian list lengths measured during testing. Colors encode counts from low to high, with purple indicating fewer Gaussians and yellow indicating more. All methods use identical tile sizes for fair comparison. Our method consistently achieves the shortest lists across all scenes. Training times (in seconds): 3DGS (919.51), Taming-3DGS (402.54), LiteGS (191.17), Ours (99.58). Additional results are provided in \ref{['fig:supplementary_gaussian_count_viz']}.
• Figure 2: Our method achieves the fastest training time while maintaining comparable reconstruction quality.
• Figure 3: Overview of our method and effects. (a) The Gaussian list of 3DGS. (b) Distribution of Gaussian list length showing our method produces significantly shorter lists. (c) Gaussian list reduction after applying scale reset. (d, e) Scale and opacity distributions comparing 3DGS and 3DGS with scale reset, showing scale reset produces smaller Gaussians with higher opacities. (f) Gaussian list reduction after applying entropy regularization. (g, h) Scale and opacity distributions comparing 3DGS and 3DGS with entropy regularization, demonstrating entropy constraint produces smaller Gaussians and more polarized opacities. “3DGS” results are produced with LiteGS.
• Figure 4: Scale reset achieves shorter Gaussian lists (limited x-range for clarity).
• Figure 5: A toy example demonstrating how entropy regularization polarizes Gaussian weights along a ray.