GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916502373924864 |
|---|---|
| author | Wang, Jiepeng Liu, Yuan Wang, Peng Lin, Cheng Hou, Junhui Li, Xin Komura, Taku Wang, Wenping |
| author_facet | Wang, Jiepeng Liu, Yuan Wang, Peng Lin, Cheng Hou, Junhui Li, Xin Komura, Taku Wang, Wenping |
| contents | 3D Gaussian Splatting has achieved impressive performance in novel view synthesis with real-time rendering capabilities. However, reconstructing high-quality surfaces with fine details using 3D Gaussians remains a challenging task. In this work, we introduce GausSurf, a novel approach to high-quality surface reconstruction by employing geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas of a scene. We observe that a scene can be mainly divided into two primary regions: 1) texture-rich and 2) texture-less areas. To enforce multi-view consistency at texture-rich areas, we enhance the reconstruction quality by incorporating a traditional patch-match based Multi-View Stereo (MVS) approach to guide the geometry optimization in an iterative scheme. This scheme allows for mutual reinforcement between the optimization of Gaussians and patch-match refinement, which significantly improves the reconstruction results and accelerates the training process. Meanwhile, for the texture-less areas, we leverage normal priors from a pre-trained normal estimation model to guide optimization. Extensive experiments on the DTU and Tanks and Temples datasets demonstrate that our method surpasses state-of-the-art methods in terms of reconstruction quality and computation time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_19454 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction Wang, Jiepeng Liu, Yuan Wang, Peng Lin, Cheng Hou, Junhui Li, Xin Komura, Taku Wang, Wenping Computer Vision and Pattern Recognition 3D Gaussian Splatting has achieved impressive performance in novel view synthesis with real-time rendering capabilities. However, reconstructing high-quality surfaces with fine details using 3D Gaussians remains a challenging task. In this work, we introduce GausSurf, a novel approach to high-quality surface reconstruction by employing geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas of a scene. We observe that a scene can be mainly divided into two primary regions: 1) texture-rich and 2) texture-less areas. To enforce multi-view consistency at texture-rich areas, we enhance the reconstruction quality by incorporating a traditional patch-match based Multi-View Stereo (MVS) approach to guide the geometry optimization in an iterative scheme. This scheme allows for mutual reinforcement between the optimization of Gaussians and patch-match refinement, which significantly improves the reconstruction results and accelerates the training process. Meanwhile, for the texture-less areas, we leverage normal priors from a pre-trained normal estimation model to guide optimization. Extensive experiments on the DTU and Tanks and Temples datasets demonstrate that our method surpasses state-of-the-art methods in terms of reconstruction quality and computation time. |
| title | GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.19454 |