HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars
Hongrui Cai, Yuting Xiao, Xuan Wang, Jiafei Li, Yudong Guo, Yanbo Fan, Shenghua Gao, Juyong Zhang
Abstract
Mesh based Avatars Ours GaussianAvatars Figure 1 . We present HERA, a novel hybrid explicit representation to model 3D head avatars efficiently and effectively. In detail, we combine the advantages of UV-mapped 3D mesh and 3DGS through the proposed hybrid rendering pipeline. On the right side, we showcase the animatable head avatars that employ the hybrid representation, illustrating that high-fidelity rendering effects are achieved across different characters, varying viewpoints and diverse expressions.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext f33858c6-7452-4c94-9bc1-425426697487Cited by top-tier papers4
- SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time EditingHeyi Sun, Cong Wang, Tian-Xing Xu, Jingwei Huang et al.ICCV 2025 · 8 citations
- UIKA: Fast Universal Head Avatar from Pose-Free ImagesZijian Wu, Boyao Zhou, Liangxiao Hu, Hongyu Liu et al.CVPR 2026 · 6 citations
- Bringing Your Portrait to 3D PresenceJiawei Zhang, Lei Chu, Jiahao Li, Zhenyu Zang et al.CVPR 2026 · 3 citations
- Scaling4D: Pushing the Frontier of Video Novel View Synthesis through Large-Scale Monocular VideosHongrui Cai, Junjie Luo, Zhihong Fu, Shengnan Zhu et al.CVPR 2026
Builds on31
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
- Volume Rendering of Neural Implicit SurfacesLior Yariv, Jiatao Gu, Yoni Kasten, Yaron LipmanNeurIPS 2021 · 1,421 citations
- Everybody Dance NowCaroline Chan, Shiry Ginosar, Tinghui Zhou, Alexei A. EfrosICCV 2019 · 840 citations
Related papers
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head EditingCong Wang, Di Kang, Heyi Sun, Shen-Han Qian et al.CVPR 2025
- GANHead: Towards Generative Animatable Neural Head AvatarsSijing Wu, Yichao Yan, Yunhao Li, Yuhao Cheng et al.CVPR 2023
- 3D Gaussian Blendshapes for Head Avatar AnimationShengjie Ma, Yanlin Weng, Tianjia Shao, Kun ZhouSIGGRAPH 2024 · 57 citations
- SplattingAvatar: Realistic Real-Time Human Avatars With Mesh-Embedded Gaussian SplattingZhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang et al.CVPR 2024 · 92 citations
- PhysHead: Simulation-Ready Gaussian Head AvatarsBerna Kabadayi, Vanessa Sklyarova, Wojciech Zielonka, Justus Thies et al.CVPR 2026 · 1 citation
