CGHair：基于发卡聚类的紧凑高斯头发重建
CGHair: Compact Gaussian Hair Reconstruction with Card Clustering
把发型内跨发丝的结构与外观相似性显式建模为发卡聚类加共享纹理码本，可直接迁移到其他高冗余 3DGS 场景（毛发、植被、织物）的紧凑化与加速；其生成先验初始化发丝几何的思路也可用于缓解 3DGS 对稠密初始化的依赖。
原文依据 we cluster strands into representative hair cards and group these into shared texture codebooks
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出了一套从多视角图像进行高保真头发重建的紧凑流程。尽管近期的三维高斯泼溅（3DGS）方法能够取得逼真的结果，但它们往往需要数百万个图元，导致高昂的存储与渲染开销。观察到同一发型内的头发在结构与外观上具有相似性，我们将发丝聚类为具有代表性的发卡，并将这些发卡归入共享的纹理码本。我们的方法将这一结构与 3DGS 渲染相结合，在保持可比视觉质量的同时显著降低重建时间与存储。此外，我们提出了一种生成先验加速方法，用于从一组图像中重建初始发丝几何。实验表明，我们的方法将发丝重建时间缩短为原来的四分之一，并在内存占用降低 200 倍以上的情况下取得可比的渲染性能。
英文原文摘要 885 字符
We present a compact pipeline for high-fidelity hair reconstruction from multi-view images. While recent 3D Gaussian Splatting (3DGS) methods achieve realistic results, they often require millions of primitives, leading to high storage and rendering costs. Observing that hair exhibits structural and visual similarities across a hairstyle, we cluster strands into representative hair cards and group these into shared texture codebooks. Our approach integrates this structure with 3DGS rendering, significantly reducing reconstruction time and storage while maintaining comparable visual quality. In addition, we propose a generative prior accelerated method to reconstruct the initial strand geometry from a set of images. Our experiments demonstrate a 4-fold reduction in strand reconstruction time and achieve comparable rendering performance with over 200x lower memory footprint.