用卡片聚类压缩毛发重建，存储降200倍，速度提升4倍。
CGHair: Compact Gaussian Hair Reconstruction with Card Clustering
- 将头发分组为代表性卡片，共享纹理码本降低冗余。
- 重建时间减少4倍，内存占用降低200倍以上，视觉质量相当。
- 适合需要高效毛发建模的影视动画与虚拟人应用。
我们提出一种紧凑的多视角图像毛发高保真重建流程。尽管近期3D高斯溅射（3DGS）方法能实现逼真效果，但通常需数百万个基础元素，导致存储和渲染成本高昂。观察到同一发型中毛发具有结构与视觉相似性，我们将其分组为代表性头发卡片，并统一到共享纹理码本中。该结构与3DGS渲染结合，显著降低重建耗时与存储开销，同时保持相近视觉质量。此外，我们提出一种生成先验加速方法，从一组图像中重建初始发丝几何。实验表明，发丝重建时间减少4倍，渲染性能相当，内存占用降低200倍以上。
原文摘要 · Abstract (English)
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.
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。