Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding
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_ | 1866911784189820928 |
|---|---|
| author | Zanjani, Farhad G. Cai, Hong Zhu, Yinhao Mirvakhabova, Leyla Porikli, Fatih |
| author_facet | Zanjani, Farhad G. Cai, Hong Zhu, Yinhao Mirvakhabova, Leyla Porikli, Fatih |
| contents | This paper presents Neural Mesh Fusion (NMF), an efficient approach for joint optimization of polygon mesh from multi-view image observations and unsupervised 3D planar-surface parsing of the scene. In contrast to implicit neural representations, NMF directly learns to deform surface triangle mesh and generate an embedding for unsupervised 3D planar segmentation through gradient-based optimization directly on the surface mesh. The conducted experiments show that NMF obtains competitive results compared to state-of-the-art multi-view planar reconstruction, while not requiring any ground-truth 3D or planar supervision. Moreover, NMF is significantly more computationally efficient compared to implicit neural rendering-based scene reconstruction approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16739 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding Zanjani, Farhad G. Cai, Hong Zhu, Yinhao Mirvakhabova, Leyla Porikli, Fatih Computer Vision and Pattern Recognition This paper presents Neural Mesh Fusion (NMF), an efficient approach for joint optimization of polygon mesh from multi-view image observations and unsupervised 3D planar-surface parsing of the scene. In contrast to implicit neural representations, NMF directly learns to deform surface triangle mesh and generate an embedding for unsupervised 3D planar segmentation through gradient-based optimization directly on the surface mesh. The conducted experiments show that NMF obtains competitive results compared to state-of-the-art multi-view planar reconstruction, while not requiring any ground-truth 3D or planar supervision. Moreover, NMF is significantly more computationally efficient compared to implicit neural rendering-based scene reconstruction approaches. |
| title | Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.16739 |