PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields
This addresses a crucial task in computer vision for applications like 3D reconstruction, but it appears incremental as it builds on neural field representations.
The paper tackles the problem of identifying dense 3D planar primitives from visual data, presenting PlanarNeRF, which enhances detection with appearance and geometry knowledge and achieves significant improvements in training efficiency and performance over prior methods.
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.