Real-time Physically Guided Hair Interpolation
Jerry Hsu, Tongtong Wang, Zherong Pan, Xifeng Gao, Cem Yuksel, Kui Wu
摘要
Strand-based hair simulations have recently become increasingly popular for a range of real-time applications. However, accurately simulating the full number of hair strands remains challenging. A commonly employed technique involves simulating a subset of guide hairs to capture the overall behavior of the hairstyle. Details are then enriched by interpolation using linear skinning. Hair interpolation enables fast real-time simulations but frequently leads to various artifacts during runtime. As the skinning weights are often pre-computed, substantial variations between the initial and deformed shapes of the hair can cause severe deviations in fine hair geometry. Straight hairs may become kinked, and curly hairs may become zigzags. This work introduces a novel physical-driven hair interpolation scheme that utilizes existing simulated guide hair data. Instead of directly operating on positions, we interpolate the internal forces from the guide hairs before efficiently reconstructing the rendered hairs based on their material model. We formulate our problem as a constraint satisfaction problem for which we present an efficient solution. Further practical considerations are addressed using regularization terms that regulate penetration avoidance and drift correction. We have tested various hairstyles to illustrate that our approach can generate visually plausible rendered hairs with only a few guide hairs and minimal computational overhead, amounting to only about 20% of conventional linear hair interpolation. This efficiency underscores the practical viability of our method for real-time applications.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- Stable Cosserat RodsJerry Hsu, Tongtong Wang, Kui Wu, Cem YukselSIGGRAPH 2025 · 被引用 9 次
- StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric PriorsXiaokun Sun, Zeyu Cai, Ying Tai, Jian Yang 等ICCV 2025 · 被引用 3 次
- DGH: Dynamic Gaussian HairJunying Wang, Yuanlu Xu, Edith Tretschk, Ziyan Wang 等NeurIPS 2025 · 被引用 2 次
- HairLRM: Strand-based Hair Modeling via Large Reconstruction ModelsYuefan Shen, Yican Dong, Xiufeng Huang, Zhongtian Zheng 等SIGGRAPH 2026
- Quaffure: Real-Time Quasi-Static Neural Hair SimulationTuur Stuyck, Gene Wei-Chin Lin, Egor Larionov, Hsiao-Yu Chen 等CVPR 2025
它引用的顶会 Paper5
- Neural Haircut: Prior-Guided Strand-Based Hair ReconstructionVanessa Sklyarova, Jenya Chelishev, Andreea Dogaru, Igor Medvedev 等ICCV 2023 · 被引用 57 次
- Revisiting integration in the material point method: a scheme for easier separation and less dissipationYun (Raymond) Fei, Qi Guo, Rundong Wu, Li Huang 等SIGGRAPH 2021 · 被引用 51 次
- Simple and scalable frictional contacts for thin nodal objectsGilles DavietSIGGRAPH 2020 · 被引用 50 次
- CT2Hair: High-Fidelity 3D Hair Modeling using Computed TomographyYuefan Shen, Shunsuke Saito, Ziyan Wang, Olivier Maury 等SIGGRAPH 2023 · 被引用 31 次
- Sag-Free Initialization for Strand-Based Hybrid Hair SimulationJerry Hsu, Tongtong Wang, Zherong Pan, Xifeng Gao 等SIGGRAPH 2023 · 被引用 22 次
相关 Paper
- Augmented Mass-Spring Model for Real-Time Dense Hair SimulationJorge Alejandro Amador Herrera, Yi Zhou, Xin Sun, Zhixin Shu 等ICCV 2025 · 被引用 1 次
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line SegmentsYusuke Takimoto, Hikari Takehara, Hiroyuki Sato, Zihao Zhu 等CVPR 2024 · 被引用 9 次
- HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance CaptureZiyan Wang, Giljoo Nam, Tuur Stuyck, Stephen Lombardi 等CVPR 2022
- Modeling Hair Strands with Roving CapsulesAlexander Reshetov, David HartSIGGRAPH 2024 · 被引用 2 次
- Real-Time Hair Rendering with Hair MeshesGaurav Bhokare, Eisen Montalvo, Elie Diaz, Cem YukselSIGGRAPH 2024 · 被引用 14 次
