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; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 16377-16387

Abstract


Neural rendering has demonstrated remarkable success in high-quality 3D neural reconstruction and novel view synthesis with dense input views and accurate poses. However, applying it to sparse, unposed views in unbounded 360* scenes remains a challenging problem. In this paper, we propose a novel neural rendering framework to accomplish the unposed and extremely sparse-view 3D reconstruction in unbounded 360* scenes. To resolve the spatial ambiguity inherent in unbounded scenes with sparse input views, we propose a layered Gaussian-based representation to effectively model the scene with distinct spatial layers. By employing a dense stereo reconstruction model to recover coarse geometry, we introduce a layer-specific bootstrap optimization to refine the noise and fill occluded regions in the reconstruction. Furthermore, we propose an iterative fusion of reconstruction and generation alongside an uncertainty-aware training approach to facilitate mutual conditioning and enhancement between these two processes. Comprehensive experiments show that our approach outperforms existing state-of-the-art methods in terms of rendering quality and surface reconstruction accuracy. Project page: https://zju3dv.github.io/free360/

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2025_CVPR, author = {Bao, Chong and Zhang, Xiyu and Yu, Zehao and Shi, Jiale and Zhang, Guofeng and Peng, Songyou and Cui, Zhaopeng}, title = {Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {16377-16387} }