CGHair: Compact Gaussian Hair Reconstruction with Card Clustering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Luo, Haimin, Sarkar, Srinjay, Mosella-Montoro, Albert, Carrasco, Francisco Vicente, De la Torre, Fernando
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908936854044672
author Luo, Haimin
Sarkar, Srinjay
Mosella-Montoro, Albert
Carrasco, Francisco Vicente
De la Torre, Fernando
author_facet Luo, Haimin
Sarkar, Srinjay
Mosella-Montoro, Albert
Carrasco, Francisco Vicente
De la Torre, Fernando
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03716
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CGHair: Compact Gaussian Hair Reconstruction with Card Clustering
Luo, Haimin
Sarkar, Srinjay
Mosella-Montoro, Albert
Carrasco, Francisco Vicente
De la Torre, Fernando
Computer Vision and Pattern Recognition
Graphics
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.
title CGHair: Compact Gaussian Hair Reconstruction with Card Clustering
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2604.03716