Perceiving Systems
Conference Paper
2025
Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photo-Realistic Appearance from Multi-View Video
arXiv project video
We introduce Gaussian Garments, a novel approach for reconstructing realistic-looking, simulation-ready garment assets from multi-view videos. Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color and high-frequency surface details. This representation enables accurate registration of garment geometries to multi-view videos and helps disentangle albedo textures from lighting effects. Furthermore, we demonstrate how a pre-trained Graph Neural Network (GNN) can be fine-tuned to replicate the real behavior of each garment. The reconstructed Gaussian Garments can be automatically combined into multi-garment outfits and animated with the fine-tuned GNN.
| Author(s): | Boxiang Rong and Artur Grigorev and Wenbo Wang and Michael J. Black and Bernhard Thomaszewski and Christina Tsalicoglou and Otmar Hilliges |
| Links: | |
| Book Title: | International Conference on 3D Vision (3DV) |
| Year: | 2025 |
| Month: | March |
| Project(s): | |
| BibTeX Type: | Conference Paper (inproceedings) |
| Event Name: | International Conference on 3D Vision |
| Event Place: | Singapore |
| State: | Published |
| URL: | https://ribosome-rbx.github.io/Gaussian-Garments/ |
BibTeX
@inproceedings{GaussGarments2024,
title = {Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photo-Realistic Appearance from Multi-View Video},
booktitle = {International Conference on 3D Vision (3DV)},
abstract = {We introduce Gaussian Garments, a novel approach for reconstructing realistic-looking, simulation-ready garment assets from multi-view videos.
Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color and high-frequency surface details.
This representation enables accurate registration of garment geometries to multi-view videos and helps disentangle albedo textures from lighting effects.
Furthermore, we demonstrate how a pre-trained Graph Neural Network (GNN) can be fine-tuned to replicate the real behavior of each garment.
The reconstructed Gaussian Garments can be automatically combined into multi-garment outfits and animated with the fine-tuned GNN.
},
month = mar,
year = {2025},
author = {Rong, Boxiang and Grigorev, Artur and Wang, Wenbo and Black, Michael J. and Thomaszewski, Bernhard and Tsalicoglou, Christina and Hilliges, Otmar},
url = {https://ribosome-rbx.github.io/Gaussian-Garments/},
month_numeric = {3}
}