# GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

arXiv: https://arxiv.org/abs/2503.10597 · HTML: https://mlsanity.com/paper/2503.10597/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 67 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces](https://mlsanity.com/paper/2311.17977/) (2023)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [Neural Reflectance Fields for Appearance Acquisition](https://mlsanity.com/paper/2008.03824/) (2020)
- [Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing](https://mlsanity.com/paper/2311.16043/) (2023)
- [Pixel Codec Avatars](https://mlsanity.com/paper/2104.04638/) (2021)
- [Relightable Gaussian Codec Avatars](https://mlsanity.com/paper/2312.03704/) (2023)
- [Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars](https://mlsanity.com/paper/2211.11208/) (2022)
- [SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color](https://mlsanity.com/paper/1902.06838/) (2019)
- [GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization](https://mlsanity.com/paper/2312.05133/) (2023)
- [PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations](https://mlsanity.com/paper/2404.04421/) (2024)
- [GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians](https://mlsanity.com/paper/2402.10483/) (2024)
- [GS^3: Efficient Relighting with Triple Gaussian Splatting](https://mlsanity.com/paper/2410.11419/) (2024)
- [Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images](https://mlsanity.com/paper/2207.14067/) (2022)
- [NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting](https://mlsanity.com/paper/2107.12351/) (2021)
- [HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture](https://mlsanity.com/paper/2112.06904/) (2021)
- [GroomCap: High-Fidelity Prior-Free Hair Capture](https://mlsanity.com/paper/2409.00831/) (2024)
- [Neural Hair Rendering](https://mlsanity.com/paper/2004.13297/) (2020)
- [Two-phase Hair Image Synthesis by Self-Enhancing Generative Model](https://mlsanity.com/paper/1902.11203/) (2019)

## Built on by (most cited first, 7 of 7)

- [3DPR: Single Image 3D Portrait Relight using Generative Priors](https://mlsanity.com/paper/2510.15846/) (2025)
- [PhysHead: Simulation-Ready Gaussian Head Avatars](https://mlsanity.com/paper/2604.06467/) (2026)
- [AvatarBack: Back-Head Generation for Complete 3D Avatars from Front-View Images](https://mlsanity.com/paper/2508.20623/) (2025)
- [CGHair: Compact Gaussian Hair Reconstruction with Card Clustering](https://mlsanity.com/paper/2604.03716/) (2026)
- [HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis](https://mlsanity.com/paper/2605.08824/) (2026)
- [Wispy to Voluminous: Prior-free Multi-view Capture of Strand-level Facial Hair](https://mlsanity.com/paper/2606.08041/) (2026)
- [HELIOS: From midnight to noon, continuous outdoor urban scene relighting](https://mlsanity.com/paper/2609.00901/) (2026)

## Abstract (arXiv)

We present GroomLight, a novel method for relightable hair appearance modeling from multi-view images. Existing hair capture methods struggle to balance photorealistic rendering with relighting capabilities. Analytical material models, while physically grounded, often fail to fully capture appearance details. Conversely, neural rendering approaches excel at view synthesis but generalize poorly to novel lighting conditions. GroomLight addresses this challenge by combining the strengths of both paradigms. It employs an extended hair BSDF model to capture primary light transport and a light-aware residual model to reconstruct the remaining details. We further propose a hybrid inverse rendering pipeline to optimize both components, enabling high-fidelity relighting, view synthesis, and material editing. Extensive evaluations on real-world hair data demonstrate state-of-the-art performance of our method.