{"ID":2879815,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15457","arxiv_id":"2508.15457","title":"Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework","abstract":"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.","short_abstract":"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-Moti...","url_abs":"https://arxiv.org/abs/2508.15457","url_pdf":"https://arxiv.org/pdf/2508.15457v1","authors":"[\"Zongqi He\",\"Hanmin Li\",\"Kin-Chung Chan\",\"Yushen Zuo\",\"Hao Xie\",\"Zhe Xiao\",\"Jun Xiao\",\"Kin-Man Lam\"]","published":"2025-08-21T11:25:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}