发表机构
Boise State University（博伊西州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文通过通道监督实验证明，标准3DGS的几何形成主要由亮度主导，色度贡献较小，且冻结几何后色度外观可被重新拟合恢复。
AI 中文摘要
标准三维高斯泼溅（3D Gaussian Splatting, 3DGS）从RGB监督中联合学习几何和外观，这使得难以分离亮度和色度对学习表示的贡献。我们通过在不同通道监督下训练模型、冻结其非外观参数（位置、尺度、旋转和不透明度）、并使用相同的求解器重新估计外观，然后比较留出重建结果来研究这一问题。在十一个基准场景中，每个场景进行四次独立运行，仅由亮度学习的几何在平均情况下支持留出重建的PSNR比由RGB训练的几何低0.085 dB。如果从训练好的模型中删除色度，一个足够有表达力的求解器可以在冻结的几何上将其重新拟合到原始质量或略优。高阶球谐函数对亮度的重建质量贡献远大于对色度的贡献，平均将PSNR提升1.44 dB，而对色度仅提升0.19 dB，尽管在镜面般的表面上，色调仍随视点变化。当几何正在形成时，亮度的优势甚至更大。仅色度监督产生的几何在相同外观求解后比仅亮度监督产生的几何差3.9-5.5 dB；致密化解释了这一差距的一部分。总体而言，标准3DGS中的几何形成强烈地以亮度为主导，但并非仅由亮度决定，并且在空间支持形成后，大部分彩色外观可以被恢复。
英文摘要
Standard 3D Gaussian Splatting (3DGS) learns geometry and appearance jointly from RGB supervision, making it difficult to isolate how luminance and chroma contribute to the learned representation. We study this by training models under different channel supervision, freezing their non-appearance parameters (position, scale, rotation, and opacity), and re-estimating appearance with the same solver before comparing held-out reconstruction. Across eleven benchmark scenes with four independent runs each, geometry learned from luminance alone supports held-out reconstruction 0.085 dB below RGB-trained geometry on average. If chroma is deleted from a trained model, a sufficiently expressive solver can re-fit it on the frozen geometry to the original quality or slightly better. Higher-order spherical harmonics contribute much more reconstruction quality to luminance than to chroma, improving PSNR by 1.44 dB versus 0.19 dB on average, although on mirror-like surfaces hue does still change with viewpoint. The luminance advantage is even larger when geometry is being formed. Chroma-only supervision produces geometry 3.9-5.5 dB worse than luminance-only supervision after the same appearance solve; densification explains part of this gap. Overall, geometry formation in standard 3DGS is strongly luminance-dominated but not luminance-exclusive, and much of the chromatic appearance can be recovered after spatial support has formed.
Comments28 pages, 6 figures, 7 tables
