五分钟重建高精度可动画虚拟人，从单视频实现几何与外观建模
InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video
- 通过几何感知的SDF正则化，稳定优化哈希网格表示
- 仅需5分钟训练即达领先重建效果，较前作提速数小时
- 适合需要快速生成可动画虚拟人的应用开发者
我们提出InstantGeoAvatar，一种从单目视频高效学习详细3D几何与外观的可动画隐式人体化身建模方法。核心观察发现：用哈希网格表示人体符号距离函数（SDF）时存在严重不稳定性与劣局部极小。为此，我们设计了一种原理性几何感知的SDF正则化方案，无缝融入体渲染流程且计算开销极小。该方案显著优于此前在哈希网格上训练SDF的方法。仅用5分钟训练时间即可实现优异的几何重建与新视角合成效果，相比之前需数小时的工作大幅提升效率。InstantGeoAvatar为实现交互式虚拟化身重建迈出关键一步。
原文摘要 · Abstract (English)
We present InstantGeoAvatar, a method for efficient and effective learning from monocular video of detailed 3D geometry and appearance of animatable implicit human avatars. Our key observation is that the optimization of a hash grid encoding to represent a signed distance function (SDF) of the human subject is fraught with instabilities and bad local minima. We thus propose a principled geometry-aware SDF regularization scheme that seamlessly fits into the volume rendering pipeline and adds negligible computational overhead. Our regularization scheme significantly outperforms previous approaches for training SDFs on hash grids. We obtain competitive results in geometry reconstruction and novel view synthesis in as little as five minutes of training time, a significant reduction from the several hours required by previous work. InstantGeoAvatar represents a significant leap forward towards achieving interactive reconstruction of virtual avatars.
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。