# 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations

arXiv: https://arxiv.org/abs/2504.14967 · HTML: https://mlsanity.com/paper/2504.14967/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 47 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 30 of 38)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes](https://mlsanity.com/paper/2312.14937/) (2023)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers](https://mlsanity.com/paper/2312.09147/) (2023)
- [Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis](https://mlsanity.com/paper/2401.02436/) (2023)
- [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](https://mlsanity.com/paper/2109.01847/) (2021)
- [HeadNeRF: A Real-time NeRF-based Parametric Head Model](https://mlsanity.com/paper/2112.05637/) (2021)
- [Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://mlsanity.com/paper/2211.11610/) (2022)
- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)
- [Instant Volumetric Head Avatars](https://mlsanity.com/paper/2211.12499/) (2022)
- [Reconstructing Personalized Semantic Facial NeRF Models From Monocular Video](https://mlsanity.com/paper/2210.06108/) (2022)
- [Relightable Gaussian Codec Avatars](https://mlsanity.com/paper/2312.03704/) (2023)
- [FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding](https://mlsanity.com/paper/2312.02214/) (2023)
- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [MoFaNeRF: Morphable Facial Neural Radiance Field](https://mlsanity.com/paper/2112.02308/) (2021)
- [MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar](https://mlsanity.com/paper/2312.04558/) (2023)
- [Neural Trajectory Fields for Dynamic Novel View Synthesis](https://mlsanity.com/paper/2105.05994/) (2021)
- [AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels](https://mlsanity.com/paper/2211.13206/) (2022)
- [Learning Neural Parametric Head Models](https://mlsanity.com/paper/2212.02761/) (2022)
- [HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting](https://mlsanity.com/paper/2312.03461/) (2023)
- [HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting](https://mlsanity.com/paper/2312.02902/) (2023)

## Built on by (most cited first, 14 of 14)

- [UIKA: Fast Universal Head Avatar from Pose-Free Images](https://mlsanity.com/paper/2601.07603/) (2026)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars](https://mlsanity.com/paper/2507.02803/) (2025)
- [AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars](https://mlsanity.com/paper/2512.06438/) (2025)
- [Face Anything: 4D Face Reconstruction from Any Image Sequence](https://mlsanity.com/paper/2604.19702/) (2026)
- [EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head](https://mlsanity.com/paper/2512.05991/) (2025)
- [AvatarPointillist: AutoRegressive 4D Gaussian Avatarization](https://mlsanity.com/paper/2604.04787/) (2026)
- [Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation](https://mlsanity.com/paper/2605.25220/) (2026)
- [MoGaFace: Momentum-Guided and Texture-Aware Gaussian Avatars for Consistent Facial Geometry](https://mlsanity.com/paper/2508.01218/) (2025)
- [SIE3D: Single-Image Expressive 3D Avatar Generation via Semantic Embedding and Perceptual Expression Loss](https://mlsanity.com/paper/2509.24004/) (2025)
- [One-shot Compositional 3D Head Avatars with Deformable Hair](https://mlsanity.com/paper/2604.14782/) (2026)
- [LentiAvatar: Pseudo-Multiview Reconstruction and Subpixel Prism Rendering for Real-Time Stereoscopic Communication](https://mlsanity.com/paper/2606.10550/) (2026)
- [MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling](https://mlsanity.com/paper/2609.12850/) (2026)
- [HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion](https://mlsanity.com/paper/2610.17348/) (2026)

## Abstract (arXiv)

Recent studies have combined 3D Gaussian and 3D Morphable Models (3DMM) to construct high-quality 3D head avatars. In this line of research, existing methods either fail to capture the dynamic textures or incur significant overhead in terms of runtime speed or storage space. To this end, we propose a novel method that addresses all the aforementioned demands. In specific, we introduce an expressive and compact representation that encodes texture-related attributes of the 3D Gaussians in the tensorial format. We store appearance of neutral expression in static tri-planes, and represents dynamic texture details for different expressions using lightweight 1D feature lines, which are then decoded into opacity offset relative to the neutral face. We further propose adaptive truncated opacity penalty and class-balanced sampling to improve generalization across different expressions. Experiments show this design enables accurate face dynamic details capturing while maintains real-time rendering and significantly reduces storage costs, thus broadening the applicability to more scenarios.