PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912264937799680 |
|---|---|
| author | Chen, Zheng Yan, Qingan Zhan, Huangying Cai, Changjiang Xu, Xiangyu Huang, Yuzhong Wang, Weihan Feng, Ziyue Xu, Yi Liu, Lantao |
| author_facet | Chen, Zheng Yan, Qingan Zhan, Huangying Cai, Changjiang Xu, Xiangyu Huang, Yuzhong Wang, Weihan Feng, Ziyue Xu, Yi Liu, Lantao |
| contents | Identifying spatially complete planar primitives from visual data is a crucial task in computer vision. Prior methods are largely restricted to either 2D segment recovery or simplifying 3D structures, even with extensive plane annotations. We present PlanarNeRF, a novel framework capable of detecting dense 3D planes through online learning. Drawing upon the neural field representation, PlanarNeRF brings three major contributions. First, it enhances 3D plane detection with concurrent appearance and geometry knowledge. Second, a lightweight plane fitting module is proposed to estimate plane parameters. Third, a novel global memory bank structure with an update mechanism is introduced, ensuring consistent cross-frame correspondence. The flexible architecture of PlanarNeRF allows it to function in both 2D-supervised and self-supervised solutions, in each of which it can effectively learn from sparse training signals, significantly improving training efficiency. Through extensive experiments, we demonstrate the effectiveness of PlanarNeRF in various scenarios and remarkable improvement over existing works. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_00871 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields Chen, Zheng Yan, Qingan Zhan, Huangying Cai, Changjiang Xu, Xiangyu Huang, Yuzhong Wang, Weihan Feng, Ziyue Xu, Yi Liu, Lantao Computer Vision and Pattern Recognition Identifying spatially complete planar primitives from visual data is a crucial task in computer vision. Prior methods are largely restricted to either 2D segment recovery or simplifying 3D structures, even with extensive plane annotations. We present PlanarNeRF, a novel framework capable of detecting dense 3D planes through online learning. Drawing upon the neural field representation, PlanarNeRF brings three major contributions. First, it enhances 3D plane detection with concurrent appearance and geometry knowledge. Second, a lightweight plane fitting module is proposed to estimate plane parameters. Third, a novel global memory bank structure with an update mechanism is introduced, ensuring consistent cross-frame correspondence. The flexible architecture of PlanarNeRF allows it to function in both 2D-supervised and self-supervised solutions, in each of which it can effectively learn from sparse training signals, significantly improving training efficiency. Through extensive experiments, we demonstrate the effectiveness of PlanarNeRF in various scenarios and remarkable improvement over existing works. |
| title | PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.00871 |