FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2min
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912973336870912 |
|---|---|
| author | Zhao, Yibin Pan, Yihan Nan, Jun Chen, Liwei Yi, Jianjun |
| author_facet | Zhao, Yibin Pan, Yihan Nan, Jun Chen, Liwei Yi, Jianjun |
| contents | Gaussian Splatting has become a leading reconstruction technique, known for its high-quality novel view synthesis and detailed reconstruction. However, most existing methods require dense, calibrated views. Reconstructing from free sparse images often leads to poor surface due to limited overlap and overfitting. We introduce FSFSplatter, a new approach for fast surface reconstruction from free sparse images. Our method integrates end-to-end dense Gaussian initialization, camera parameter estimation, and geometry-enhanced scene optimization. Specifically, FSFSplatter employs a large Transformer to encode multi-view images and generates a dense and geometrically consistent Gaussian scene initialization via a self-splitting Gaussian head. It eliminates local floaters through contribution-based pruning and mitigates overfitting to limited views by leveraging depth and multi-view feature supervision with differentiable camera parameters during rapid optimization. FSFSplatter outperforms current state-of-the-art methods on widely used DTU, Replica, and BlendedMVS datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02691 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2min Zhao, Yibin Pan, Yihan Nan, Jun Chen, Liwei Yi, Jianjun Computer Vision and Pattern Recognition Graphics Gaussian Splatting has become a leading reconstruction technique, known for its high-quality novel view synthesis and detailed reconstruction. However, most existing methods require dense, calibrated views. Reconstructing from free sparse images often leads to poor surface due to limited overlap and overfitting. We introduce FSFSplatter, a new approach for fast surface reconstruction from free sparse images. Our method integrates end-to-end dense Gaussian initialization, camera parameter estimation, and geometry-enhanced scene optimization. Specifically, FSFSplatter employs a large Transformer to encode multi-view images and generates a dense and geometrically consistent Gaussian scene initialization via a self-splitting Gaussian head. It eliminates local floaters through contribution-based pruning and mitigates overfitting to limited views by leveraging depth and multi-view feature supervision with differentiable camera parameters during rapid optimization. FSFSplatter outperforms current state-of-the-art methods on widely used DTU, Replica, and BlendedMVS datasets. |
| title | FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2min |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2510.02691 |