Awesome
<img alt="image" src='media/lady-gaga.png' height="30px"> Gaga : Group Any Gaussians via 3D-aware Memory Bank
Weijie Lyu, Xueting Li, Abhijit Kundu, Yi-Hsuan Tsai, Ming-Hsuan Yang<br> University of California, Merced - Nvidia - Google
<div align='center'> <img alt="image" src='media/teaser.png'> </div>Gaga groups any Gaussians in an open-world 3D scene and renders multi-view consistent segmentation.<br> Codes will be released soon.<br> If you need the codes now, please contact the first author via email (wlyu3@ucmerced.edu).
Results
πΊοΈ Open-world 3D Segmentation
MipNeRF 360
https://github.com/weijielyu/Gaga/assets/47323245/62a7ff01-30da-4c5e-ab79-c60c091935c1
Replica
https://github.com/weijielyu/Gaga/assets/47323245/d0d5eece-c838-4be9-a3b9-71d051e97270
ScanNet
https://github.com/weijielyu/Gaga/assets/47323245/f1099e6b-40e1-46af-9c14-f480765065bf
ποΈ Scene Editing
β¨ Change the color of cushion on <img src="media/footstool.png" width="50"> to maroon π₯<br> β¨ Remove <img src="media/stuffed.png" width="50">
https://github.com/weijielyu/Gaga/assets/47323245/803f049f-8930-445c-bc1a-b8bb12df0fbf
Citation
If you find our work useful for your project, please consider citing our paper.
@misc{lyu2024gaga,
title={Gaga: Group Any Gaussians via 3D-aware Memory Bank},
author={Weijie Lyu and Xueting Li and Abhijit Kundu and Yi-Hsuan Tsai and Ming-Hsuan Yang},
year={2024},
eprint={2404.07977},
archivePrefix={arXiv},
primaryClass={cs.CV}
}