PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields
Zheng Chen, Qingan Yan, Huangying Zhan, Changjiang Cai, Xiangyu Xu, Yuzhong Huang, Weihan Wang, Ziyue Feng
Abstract
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 used 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 real-world scenarios and remarkable improvement in 3D plane detection over existing works.
BibTeX
@inproceedings{icra2025_planarnerfonline,
title = {PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields},
author = {Zheng Chen and Qingan Yan and Huangying Zhan and Changjiang Cai and Xiangyu Xu and Yuzhong Huang and Weihan Wang and Ziyue Feng and Yi Xu and Lantao Liu},
booktitle = {ICRA 2025},
year = {2025}
}