Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914701192986624 |
|---|---|
| author | Guo, Shuai Wang, Qiuwen Gao, Yijie Xie, Rong Song, Li |
| author_facet | Guo, Shuai Wang, Qiuwen Gao, Yijie Xie, Rong Song, Li |
| contents | Novel-view synthesis with sparse input views is important for real-world applications like AR/VR and autonomous driving. Recent methods have integrated depth information into NeRFs for sparse input synthesis, leveraging depth prior for geometric and spatial understanding. However, most existing works tend to overlook inaccuracies within depth maps and have low time efficiency. To address these issues, we propose a depth-guided robust and fast point cloud fusion NeRF for sparse inputs. We perceive radiance fields as an explicit voxel grid of features. A point cloud is constructed for each input view, characterized within the voxel grid using matrices and vectors. We accumulate the point cloud of each input view to construct the fused point cloud of the entire scene. Each voxel determines its density and appearance by referring to the point cloud of the entire scene. Through point cloud fusion and voxel grid fine-tuning, inaccuracies in depth values are refined or substituted by those from other views. Moreover, our method can achieve faster reconstruction and greater compactness through effective vector-matrix decomposition. Experimental results underline the superior performance and time efficiency of our approach compared to state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02063 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views Guo, Shuai Wang, Qiuwen Gao, Yijie Xie, Rong Song, Li Computer Vision and Pattern Recognition Novel-view synthesis with sparse input views is important for real-world applications like AR/VR and autonomous driving. Recent methods have integrated depth information into NeRFs for sparse input synthesis, leveraging depth prior for geometric and spatial understanding. However, most existing works tend to overlook inaccuracies within depth maps and have low time efficiency. To address these issues, we propose a depth-guided robust and fast point cloud fusion NeRF for sparse inputs. We perceive radiance fields as an explicit voxel grid of features. A point cloud is constructed for each input view, characterized within the voxel grid using matrices and vectors. We accumulate the point cloud of each input view to construct the fused point cloud of the entire scene. Each voxel determines its density and appearance by referring to the point cloud of the entire scene. Through point cloud fusion and voxel grid fine-tuning, inaccuracies in depth values are refined or substituted by those from other views. Moreover, our method can achieve faster reconstruction and greater compactness through effective vector-matrix decomposition. Experimental results underline the superior performance and time efficiency of our approach compared to state-of-the-art baselines. |
| title | Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.02063 |