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

TL;DR

This paper introduces training strategies that shorten Gaussian lists in 3D Gaussian splatting, significantly improving learning efficiency while maintaining high rendering quality.

Contribution

It proposes novel Gaussian shrinking and entropy-based sharpening techniques, along with a resolution scheduler, to accelerate 3D Gaussian learning.

Findings

Faster training with shorter Gaussian lists.

Maintains comparable rendering quality to state-of-the-art.

Demonstrates efficiency gains on benchmark datasets.

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.