Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction
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_ | 1866917626847952896 |
|---|---|
| author | Lyu, Xiaoyang Chang, Chirui Dai, Peng Sun, Yang-Tian Qi, Xiaojuan |
| author_facet | Lyu, Xiaoyang Chang, Chirui Dai, Peng Sun, Yang-Tian Qi, Xiaojuan |
| contents | Scene reconstruction from multi-view images is a fundamental problem in computer vision and graphics. Recent neural implicit surface reconstruction methods have achieved high-quality results; however, editing and manipulating the 3D geometry of reconstructed scenes remains challenging due to the absence of naturally decomposed object entities and complex object/background compositions. In this paper, we present Total-Decom, a novel method for decomposed 3D reconstruction with minimal human interaction. Our approach seamlessly integrates the Segment Anything Model (SAM) with hybrid implicit-explicit neural surface representations and a mesh-based region-growing technique for accurate 3D object decomposition. Total-Decom requires minimal human annotations while providing users with real-time control over the granularity and quality of decomposition. We extensively evaluate our method on benchmark datasets and demonstrate its potential for downstream applications, such as animation and scene editing. The code is available at https://github.com/CVMI-Lab/Total-Decom.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19314 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction Lyu, Xiaoyang Chang, Chirui Dai, Peng Sun, Yang-Tian Qi, Xiaojuan Computer Vision and Pattern Recognition Scene reconstruction from multi-view images is a fundamental problem in computer vision and graphics. Recent neural implicit surface reconstruction methods have achieved high-quality results; however, editing and manipulating the 3D geometry of reconstructed scenes remains challenging due to the absence of naturally decomposed object entities and complex object/background compositions. In this paper, we present Total-Decom, a novel method for decomposed 3D reconstruction with minimal human interaction. Our approach seamlessly integrates the Segment Anything Model (SAM) with hybrid implicit-explicit neural surface representations and a mesh-based region-growing technique for accurate 3D object decomposition. Total-Decom requires minimal human annotations while providing users with real-time control over the granularity and quality of decomposition. We extensively evaluate our method on benchmark datasets and demonstrate its potential for downstream applications, such as animation and scene editing. The code is available at https://github.com/CVMI-Lab/Total-Decom.git. |
| title | Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.19314 |