Primitive Fitting Using Deep Boundary Aware Geometric Segmentation

TL;DR

BAGSFit is a deep learning framework that segments point clouds into primitive hypotheses and verifies them geometrically, improving primitive fitting accuracy in noisy, cluttered scenes.

Contribution

It introduces a novel deep boundary-aware segmentation approach for primitive fitting that outperforms traditional methods like RANSAC in noisy environments.

Findings

BAGSFit achieves higher accuracy than RANSAC-based methods.

The framework effectively handles noisy and cluttered point clouds.

Experimental results show superior performance on both simulated and real data.

Abstract

To identify and fit geometric primitives (e.g., planes, spheres, cylinders, cones) in a noisy point cloud is a challenging yet beneficial task for fields such as robotics and reverse engineering. As a multi-model multi-instance fitting problem, it has been tackled with different approaches including RANSAC, which however often fit inferior models in practice with noisy inputs of cluttered scenes. Inspired by the corresponding human recognition process, and benefiting from the recent advancements in image semantic segmentation using deep neural networks, we propose BAGSFit as a new framework addressing this problem. Firstly, through a fully convolutional neural network, the input point cloud is point-wisely segmented into multiple classes divided by jointly detected instance boundaries without any geometric fitting. Thus, segments can serve as primitive hypotheses with a probability estimation of associating primitive classes. Finally, all hypotheses are sent through a geometric verification to correct any misclassification by fitting primitives respectively. We performed training using simulated range images and tested it with both simulated and real-world point clouds. Quantitative and qualitative experiments demonstrated the superiority of BAGSFit.