Gaga : Group Any Gaussians via 3D-aware Memory Bank

Weijie Lyu, Xueting Li, Abhijit Kundu, Yi-Hsuan Tsai, Ming-Hsuan Yang
University of California, Merced - Nvidia - Google

Gaga groups any Gaussians in an open-world 3D scene and renders multi-view consistent segmentation.
Codes will be released soon.
If you need the codes now, please contact the first author via email (wlyu3@ucmerced.edu).

Results

🗺️ Open-world 3D Segmentation

MipNeRF 360

MipNeRF_360.mov

Replica

Replica.mov

ScanNet

ScanNet.mov

🖌️ Scene Editing

✨ Change the color of cushion on to maroon 🟥
✨ Remove

scene_editing.mov

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}
}