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

2026-03-10

AI Summary

This work addresses the efficiency bottleneck in 3D Gaussian Splatting (3DGS) training caused by excessively long per-pixel Gaussian lists. To mitigate this issue, the authors propose an efficient optimization strategy that dynamically resets Gaussian scales to reduce their spatial extent and introduces an entropy constraint during alpha blending to encourage more concentrated weight distributions. This significantly reduces the number of Gaussians required per pixel. Combined with a progressive resolution scheduling scheme, the method enables each Gaussian to focus more effectively on dominant pixels, thereby minimizing redundant computations. Experimental results demonstrate that the proposed approach substantially improves both training and rendering efficiency on standard benchmarks while preserving high-quality visual fidelity.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Efficient ML / Green AI

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• 3D Gaussian splatting
• radiance field
• rendering efficiency
• Gaussian list
• training acceleration

Innovation

• 3D Gaussian Splatting
• Gaussian List Shortening
• Entropy Constraint
• Scale Resetting
• Resolution Scheduler