arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.09997cs.GRcs.CV
收藏

CLoD-GS:通过3D高斯散射实现连续细节层次

CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting

Tsinghua University(清华大学);AMAP(高德地图)

Zhigang Cheng, Mingchao Sun, Yu Liu, Zengye Ge, Luyang Tang, Mu Xu, Yangyan Li, Peng Pan

AI总结:

本文提出CLoD-GS框架,利用3D高斯散射技术实现连续细节层次,通过动态调整高斯体透明度,实现单模型的平滑细节渐变,减少存储开销和视觉瑕疵。

摘要:

细节层次(LoD)是实时计算机图形学中用于管理复杂场景渲染成本并保持视觉保真的基本技术。传统上,LoD通过离散层次(DLoD)实现,即在不同距离下切换多个模型版本。然而,这种传统范式存在两个主要缺点:需要大量存储多个模型副本,并在切换时导致视觉‘跳跃’伪影,影响用户体验。我们主张新兴的3D高斯散射(3DGS)技术的显式、原始基础性质可以实现更理想的范式:连续LoD(CLoD)。CLoD方法可以在单个统一模型内实现平滑、无缝的质量缩放,从而克服DLoD的核心问题。为此,我们引入CLoD-GS框架,将连续LoD机制直接集成到3DGS表示中。我们的方法为每个高斯原始体引入一个可学习的距离依赖衰减参数,动态调整其透明度基于视角接近度。这使得能够逐步、平滑地过滤不重要的原始体,从而在单个模型内创建连续的细节谱。为了训练模型在所有距离上都具有鲁棒性,我们引入虚拟距离缩放机制和一种新的由粗到细的训练策略,结合渲染点数正则化。我们的方法不仅消除了离散方法的存储开销和视觉瑕疵,还减少了最终模型的原始体数量和内存足迹。大量实验表明,CLoD-GS能够在单个模型中实现平滑、质量可缩放的渲染,提供在广泛性能目标下的高质量结果。

英文摘要:

Level of Detail (LoD) is a fundamental technique in real-time computer graphics for managing the rendering costs of complex scenes while preserving visual fidelity. Traditionally, LoD is implemented using discrete levels (DLoD), where multiple, distinct versions of a model are swapped out at different distances. This long-standing paradigm, however, suffers from two major drawbacks: it requires significant storage for multiple model copies and causes jarring visual ``popping" artifacts during transitions, degrading the user experience. We argue that the explicit, primitive-based nature of the emerging 3D Gaussian Splatting (3DGS) technique enables a more ideal paradigm: Continuous LoD (CLoD). A CLoD approach facilitates smooth, seamless quality scaling within a single, unified model, thereby circumventing the core problems of DLOD. To this end, we introduce CLoD-GS, a framework that integrates a continuous LoD mechanism directly into a 3DGS representation. Our method introduces a learnable, distance-dependent decay parameter for each Gaussian primitive, which dynamically adjusts its opacity based on viewpoint proximity. This allows for the progressive and smooth filtering of less significant primitives, effectively creating a continuous spectrum of detail within one model. To train this model to be robust across all distances, we introduce a virtual distance scaling mechanism and a novel coarse-to-fine training strategy with rendered point count regularization. Our approach not only eliminates the storage overhead and visual artifacts of discrete methods but also reduces the primitive count and memory footprint of the final model. Extensive experiments demonstrate that CLoD-GS achieves smooth, quality-scalable rendering from a single model, delivering high-fidelity results across a wide range of performance targets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑