MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition

TL;DR

MIGS introduces a tensor-based neural representation that efficiently models multiple human identities from monocular videos, enabling robust animation and extension to unseen identities with fewer parameters.

Contribution

The paper presents a novel tensor decomposition approach for multi-identity 3D Gaussian Splatting, reducing parameters and improving robustness over existing methods.

Findings

Outperforms existing multi-identity 3D avatar methods.

Enables robust animation under challenging poses.

Can extend to unseen identities.

Abstract

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.