Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911114107813888 |
|---|---|
| author | He, Zongqi Li, Hanmin Chan, Kin-Chung Zuo, Yushen Xie, Hao Xiao, Zhe Xiao, Jun Lam, Kin-Man |
| author_facet | He, Zongqi Li, Hanmin Chan, Kin-Chung Zuo, Yushen Xie, Hao Xiao, Zhe Xiao, Jun Lam, Kin-Man |
| contents | 3D Gaussian Splatting (3DGS) has demonstrated remarkable real-time performance in novel view synthesis, yet its effectiveness relies heavily on dense multi-view inputs with precisely known camera poses, which are rarely available in real-world scenarios. When input views become extremely sparse, the Structure-from-Motion (SfM) method that 3DGS depends on for initialization fails to accurately reconstruct the 3D geometric structures of scenes, resulting in degraded rendering quality. In this paper, we propose a novel SfM-free 3DGS-based method that jointly estimates camera poses and reconstructs 3D scenes from extremely sparse-view inputs. Specifically, instead of SfM, we propose a dense stereo module to progressively estimates camera pose information and reconstructs a global dense point cloud for initialization. To address the inherent problem of information scarcity in extremely sparse-view settings, we propose a coherent view interpolation module that interpolates camera poses based on training view pairs and generates viewpoint-consistent content as additional supervision signals for training. Furthermore, we introduce multi-scale Laplacian consistent regularization and adaptive spatial-aware multi-scale geometry regularization to enhance the quality of geometrical structures and rendered content. Experiments show that our method significantly outperforms other state-of-the-art 3DGS-based approaches, achieving a remarkable 2.75dB improvement in PSNR under extremely sparse-view conditions (using only 2 training views). The images synthesized by our method exhibit minimal distortion while preserving rich high-frequency details, resulting in superior visual quality compared to existing techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15457 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework He, Zongqi Li, Hanmin Chan, Kin-Chung Zuo, Yushen Xie, Hao Xiao, Zhe Xiao, Jun Lam, Kin-Man Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) has demonstrated remarkable real-time performance in novel view synthesis, yet its effectiveness relies heavily on dense multi-view inputs with precisely known camera poses, which are rarely available in real-world scenarios. When input views become extremely sparse, the Structure-from-Motion (SfM) method that 3DGS depends on for initialization fails to accurately reconstruct the 3D geometric structures of scenes, resulting in degraded rendering quality. In this paper, we propose a novel SfM-free 3DGS-based method that jointly estimates camera poses and reconstructs 3D scenes from extremely sparse-view inputs. Specifically, instead of SfM, we propose a dense stereo module to progressively estimates camera pose information and reconstructs a global dense point cloud for initialization. To address the inherent problem of information scarcity in extremely sparse-view settings, we propose a coherent view interpolation module that interpolates camera poses based on training view pairs and generates viewpoint-consistent content as additional supervision signals for training. Furthermore, we introduce multi-scale Laplacian consistent regularization and adaptive spatial-aware multi-scale geometry regularization to enhance the quality of geometrical structures and rendered content. Experiments show that our method significantly outperforms other state-of-the-art 3DGS-based approaches, achieving a remarkable 2.75dB improvement in PSNR under extremely sparse-view conditions (using only 2 training views). The images synthesized by our method exhibit minimal distortion while preserving rich high-frequency details, resulting in superior visual quality compared to existing techniques. |
| title | Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.15457 |