提出高效动态场景3D高斯点渲染框架，解决训练慢、数据量大问题。
Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content
- 按尺度分层组织高斯球，粗粒度控制细节激活
- 混合变形与生成策略，有效建模帧间运动
- 双向自适应掩码过滤静态区域，提升训练效率
3D高斯点渲染（3DGS）实现了高保真实时渲染，是沉浸式应用的关键。然而，将3DGS扩展到动态场景仍受限于密集高斯点的数据量及每帧训练时间过长。本文提出 \\(\M\\) 框架，专为流式任务设计的可扩展高斯点渲染方法。具体而言，基于锚点结构对高斯球按尺度分层组织：粗粒度高斯表示场景低分辨率结构，细粒度高斯由粗粒度激活以实现高保真细节渲染。为降低计算开销，引入混合形变与生成策略，通过高斯形变建模帧间运动，并触发高斯生成以表征大范围运动。此外，双向自适应掩码机制通过移除静态区域并优先选择信息丰富的视角，进一步提升训练效率。大量实验表明，\M~在显著缩短训练时间的同时，达到优于现有方法的视觉质量。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, a key requirement for immersive applications. However, the extension of 3DGS to dynamic scenes remains limitations on the substantial data volume of dense Gaussians and the prolonged training time required for each frame. This paper presents \M, a scalable Gaussian Splatting framework designed for efficient training in streaming tasks. Specifically, Gaussian spheres are hierarchically organized by scale within an anchor-based structure. Coarser-level Gaussians represent the low-resolution structure of the scene, while finer-level Gaussians, responsible for detailed high-fidelity rendering, are selectively activated by the coarser-level Gaussians. To further reduce computational overhead, we introduce a hybrid deformation and spawning strategy that models motion of inter-frame through Gaussian deformation and triggers Gaussian spawning to characterize wide-range motion. Additionally, a bidirectional adaptive masking mechanism enhances training efficiency by removing static regions and prioritizing informative viewpoints. Extensive experiments demonstrate that \M~ achieves superior visual quality while significantly reducing training time compared to state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。