3DGS-Avatar：通过可变形 3D Gaussian Splatting 实现可动画化化身
3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
AI总结：
提出基于可变形 3DGS 的单目视频可动画着装化身方法，结合非刚性变形与等距正则化，实现 30 分钟训练、50+ FPS 渲染及更优泛化。
摘要：
我们提出一种利用 3D Gaussian Splatting（3DGS）从单目视频创建可动画化人类化身的方法。现有基于神经辐射场（NeRF）的方法能够实现高质量的新视角/新姿态图像合成，但通常需要数天训练，并且在推理时极其缓慢。近来，研究界探索了用于高效训练着装化身的快速网格结构。尽管训练速度极快，这些方法几乎无法达到约 15 FPS 的交互式渲染帧率。本文使用 3D Gaussian Splatting，并学习一个非刚性变形网络来重建可动画化的着装人类化身，该化身可在 30 分钟内完成训练，并以实时帧率（50+ FPS）渲染。鉴于我们表示的显式特性，我们进一步在高斯均值向量和协方差矩阵上引入尽可能等距的正则化，以增强模型在高度关节化且未见过的姿态上的泛化能力。实验结果表明，与从单目输入创建可动画化身的最先进方法相比，我们的方法取得了相当甚至更优的性能，同时训练和推理速度分别快 400 倍和 250 倍。
英文摘要：
We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). Existing methods based on neural radiance fields (NeRFs) achieve high-quality novel-view/novel-pose image synthesis but often require days of training, and are extremely slow at inference time. Recently, the community has explored fast grid structures for efficient training of clothed avatars. Albeit being extremely fast at training, these methods can barely achieve an interactive rendering frame rate with around 15 FPS. In this paper, we use 3D Gaussian Splatting and learn a non-rigid deformation network to reconstruct animatable clothed human avatars that can be trained within 30 minutes and rendered at real-time frame rates (50+ FPS). Given the explicit nature of our representation, we further introduce as-isometric-as-possible regularizations on both the Gaussian mean vectors and the covariance matrices, enhancing the generalization of our model on highly articulated unseen poses. Experimental results show that our method achieves comparable and even better performance compared to state-of-the-art approaches on animatable avatar creation from a monocular input, while being 400x and 250x faster in training and inference, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
