用神经场+动态关键点引导，高效重建高保真3D人脸
GLVD: Guided Learned Vertex Descent
- 结合神经场优化与动态关键点引导，逐顶点迭代精修网格
- 单视图下达到当前最佳性能，推理速度显著提升
- 适合需要快速高质量3D人脸重建的场景
现有3D人脸建模方法通常依赖3D可变形模型，其表达能力受限于固定形状先验。基于优化的方法虽能生成高质量重建结果，但计算成本较高。本文提出GLVD，一种从少样本图像进行3D人脸重建的混合方法，通过引入每顶点神经场优化与动态预测的3D关键点全局结构引导，扩展了学习顶点下降（LVD）方法。结合相对空间编码，GLVD在无需密集3D监督的情况下迭代优化网格顶点，实现高表达力且灵活的几何重建，同时保持计算效率。在单视图设置下取得当前最优性能，并在多视图场景中仍具竞争力，推理时间大幅减少。
原文摘要 · Abstract (English)
Existing 3D face modeling methods usually depend on 3D Morphable Models, which inherently constrain the representation capacity to fixed shape priors. Optimization-based approaches offer high-quality reconstructions but tend to be computationally expensive. In this work, we introduce GLVD, a hybrid method for 3D face reconstruction from few-shot images that extends Learned Vertex Descent (LVD) by integrating per-vertex neural field optimization with global structural guidance from dynamically predicted 3D keypoints. By incorporating relative spatial encoding, GLVD iteratively refines mesh vertices without requiring dense 3D supervision. This enables expressive and adaptable geometry reconstruction while maintaining computational efficiency. GLVD achieves state-of-the-art performance in single-view settings and remains highly competitive in multi-view scenarios, all while substantially reducing inference time.
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。