用紧凑张量表示法实现高动态表情的实时3D人脸渲染。
3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations
- 用张量格式编码3D高斯纹理属性，分静态与动态两部分存储。
- 实测支持实时渲染且存储成本显著降低，动态细节还原准确。
- 适合需要轻量化、高保真人脸动画的应用场景。
近期研究将3D高斯与3D可变形模型（3DMM）结合构建高质量3D人脸头像。现有方法或无法捕捉动态纹理，或在运行时效率与存储空间上开销过大。为此，我们提出一种新方法：通过张量形式编码3D高斯的纹理属性。将中性表情外观存于静态三平面（tri-planes），不同表情的动态纹理细节则用轻量级1D特征线表示，并解码为相对于中性脸的透明度偏移。进一步引入自适应截断透明度惩罚和类别平衡采样，提升跨表情泛化能力。实验表明，该设计在保持实时渲染的同时显著降低存储开销，精准捕捉面部动态细节，拓展了其在更多场景中的适用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。