SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909259991613440 |
|---|---|
| author | Chen, Yiyang Dong, Siyan Wang, Xulong Cai, Lulu Zheng, Youyi Yang, Yanchao |
| author_facet | Chen, Yiyang Dong, Siyan Wang, Xulong Cai, Lulu Zheng, Youyi Yang, Yanchao |
| contents | 3D surface reconstruction from images is essential for numerous applications. Recently, Neural Radiance Fields (NeRFs) have emerged as a promising framework for 3D modeling. However, NeRFs require accurate camera poses as input, and existing methods struggle to handle significantly noisy pose estimates (i.e., outliers), which are commonly encountered in real-world scenarios. To tackle this challenge, we present a novel approach that optimizes radiance fields with scene graphs to mitigate the influence of outlier poses. Our method incorporates an adaptive inlier-outlier confidence estimation scheme based on scene graphs, emphasizing images of high compatibility with the neighborhood and consistency in the rendering quality. We also introduce an effective intersection-over-union (IoU) loss to optimize the camera pose and surface geometry, together with a coarse-to-fine strategy to facilitate the training. Furthermore, we propose a new dataset containing typical outlier poses for a detailed evaluation. Experimental results on various datasets consistently demonstrate the effectiveness and superiority of our method over existing approaches, showcasing its robustness in handling outliers and producing high-quality 3D reconstructions. Our code and data are available at: \url{https://github.com/Iris-cyy/SG-NeRF}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12667 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization Chen, Yiyang Dong, Siyan Wang, Xulong Cai, Lulu Zheng, Youyi Yang, Yanchao Computer Vision and Pattern Recognition 3D surface reconstruction from images is essential for numerous applications. Recently, Neural Radiance Fields (NeRFs) have emerged as a promising framework for 3D modeling. However, NeRFs require accurate camera poses as input, and existing methods struggle to handle significantly noisy pose estimates (i.e., outliers), which are commonly encountered in real-world scenarios. To tackle this challenge, we present a novel approach that optimizes radiance fields with scene graphs to mitigate the influence of outlier poses. Our method incorporates an adaptive inlier-outlier confidence estimation scheme based on scene graphs, emphasizing images of high compatibility with the neighborhood and consistency in the rendering quality. We also introduce an effective intersection-over-union (IoU) loss to optimize the camera pose and surface geometry, together with a coarse-to-fine strategy to facilitate the training. Furthermore, we propose a new dataset containing typical outlier poses for a detailed evaluation. Experimental results on various datasets consistently demonstrate the effectiveness and superiority of our method over existing approaches, showcasing its robustness in handling outliers and producing high-quality 3D reconstructions. Our code and data are available at: \url{https://github.com/Iris-cyy/SG-NeRF}. |
| title | SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.12667 |