高动态范围3D高斯散射 via 光亮度-色度分解
High Dynamic Range 3D Gaussian Splatting via Luminance-Chromaticity Decomposition
AI总结：
本文提出基于光亮度-色度分解的3D高斯散射方法，通过解耦亮度与色度参数，提升学习灵活性，实现更高效的高动态范围3D重建。
摘要：
高动态范围（HDR）3D重建在电影制作和虚拟生产中至关重要。现有方法通常依赖多曝光低动态范围（LDR）监督来约束学习过程，导致复杂双分支架构。本文探讨了在HDR数据空间中学习HDR3D模型的可行性，以简化模型设计。通过分析HDR影像中的3D高斯散射（3DGS），我们发现其失败源于球面谐波（SHs）在不同视角下捕捉极端辐射变化的能力有限，通常偏向高辐射观测并欠拟合。尽管增加最大SH阶数可提高训练拟合度，但会导致严重过拟合和参数开销过大。为此，我们提出了光亮度-色度分解高斯散射（LCD-GS）。通过将亮度和色度解耦为独立参数，LCD-GS显著增强了学习灵活性，参数增加极小（例如，每个基本体增加一个额外标量）。值得注意的是，LCD-GS保持了原始训练和推理流程，仅需改变颜色表示。这种显式分解自然地在推理过程中实现了基本体级别的局部和全局亮度编辑。在合成和真实数据集上的广泛实验表明，即使在更简单、更高效的架构下，LCD-GS在重建保真度和动态范围保持方面也优于现有最先进方法，为专业级HDR3D建模提供了一个优雅的范式。代码和数据集将被发布。
英文摘要：
High Dynamic Range (HDR) 3D reconstruction is pivotal for professional content creation in filmmaking and virtual production. Existing methods typically rely on multi-exposure Low Dynamic Range (LDR) supervision to constrain the learning process within vast brightness spaces, resulting in complex, dual-branch architectures. This work explores the feasibility of learning HDR 3D models exclusively in the HDR data space to simplify model design. By analyzing 3D Gaussian Splatting (3DGS) for HDR imagery, we reveal that its failure stems from the limited capacity of Spherical Harmonics (SHs) to capture extreme radiance variations across views, often biasing towards high-radiance observations and underfitting. While increasing the maximum SH degree improves training fitting, it leads to severe overfitting and excessive parameter overhead. To address this, we propose \textit{Luminance--Chromaticity Decomposition Gaussian Splatting} (LCD-GS). By decoupling luminance and chromaticity into independent parameters, LCD-GS significantly enhances learning flexibility with minimal parameter increase (\textit{e.g.}, one extra scalar per primitive). Notably, LCD-GS maintains the original training and inference pipeline, requiring only a change in color representation. This explicit decomposition naturally enables primitive-level local and global luminance editing during inference. Extensive experiments on synthetic and real datasets demonstrate that LCD-GS consistently outperforms state-of-the-art methods in reconstruction fidelity and dynamic-range preservation even with a simpler, more efficient architecture, providing an elegant paradigm for professional-grade HDR 3D modeling. Code and datasets will be released.
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。
