MIGS：基于张量分解的多身份高斯泼溅
MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition
AI总结：
本工作提出MIGS方法，利用张量分解构建多身份统一的高斯泼溅表示，仅需单目视频即可在任意姿态下鲁棒动画化多个人体，显著减少参数并优于现有方法，且可扩展至未见身份。
摘要：
我们提出了MIGS（多身份高斯泼溅），一种新颖的方法，仅使用单目视频即可为多个身份学习单一神经表示。最近的用于人体虚拟形象的3D高斯泼溅（3DGS）方法需要针对每个身份进行优化。然而，学习多身份表示在任意姿态下鲁棒地动画化人体方面具有优势。我们提出构建一个高阶张量，该张量结合了所有训练身份的所有可学习3DGS参数。通过假设低秩结构并对张量进行分解，我们在一个统一的网络中建模多个主体的复杂刚性和非刚性变形，显著减少了总参数数量。我们提出的方法利用了所有训练身份的信息，并能在具有挑战性的未见姿态下实现鲁棒动画，优于现有方法。它还可以扩展以学习未见身份。
英文摘要：
We introduce MIGS (Multi-Identity Gaussian Splatting), a novel method that learns a single neural representation for multiple identities, using only monocular videos. Recent 3D Gaussian Splatting (3DGS) approaches for human avatars require per-identity optimization. However, learning a multi-identity representation presents advantages in robustly animating humans under arbitrary poses. We propose to construct a high-order tensor that combines all the learnable 3DGS parameters for all the training identities. By assuming a low-rank structure and factorizing the tensor, we model the complex rigid and non-rigid deformations of multiple subjects in a unified network, significantly reducing the total number of parameters. Our proposed approach leverages information from all the training identities and enables robust animation under challenging unseen poses, outperforming existing approaches. It can also be extended to learn unseen identities.
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。
