تقرير
MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition
| العنوان: | MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition |
|---|---|
| المؤلفون: | Chatziagapi, Aggelina, Chrysos, Grigorios G., Samaras, Dimitris |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | 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. Comment: Accepted by ECCV 2024. Project page: https://aggelinacha.github.io/MIGS/ |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2407.07284 |
| رقم الأكسشن: | edsarx.2407.07284 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |