MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition
This addresses the need for efficient multi-identity human avatar animation in computer vision, though it is incremental as it builds on 3D Gaussian Splatting methods.
The paper tackles the problem of learning a single neural representation for multiple human identities from monocular videos, enabling robust animation under arbitrary poses and reducing parameters through tensor decomposition, outperforming existing approaches.
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.