Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views

Project Page | Video | Paper

Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views

Chong Bao, Xiyu Zhang, Zehao Yu, Jiale Shi, Guofeng Zhang, Songyou Peng, Zhaopeng Cui.

CVPR 2025

To-do

• Release training code.
• Release checkpoints.

Dataset

We use Mip-NeRF 360 and Tanks and Temples as benchmark datasets. Their sparse-view splits used in paper can be downloaded here.

Citing

@inproceedings{bao2025free,
    title={Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views},
    author={Bao, Chong and Zhang, Xiyu and Yu, Zehao and Shi, Jiale and Zhang, Guofeng and Peng, Songyou and Cui, Zhaopeng
    },
    booktitle={The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)},
    year={2025}
}