Geometric Multi-Model Fitting by Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach to improve geometric multi-model fitting from noisy point cloud data, reducing the number of iterations needed for accurate fitting.

Contribution

It formulates multi-model fitting as a sequential decision process and applies deep reinforcement learning to optimize the fitting procedure.

Findings

Significantly fewer fitting iterations compared to state-of-the-art methods.

Effective handling of noisy, unstructured point cloud data.

Demonstrated on simulated data with promising results.

Abstract

This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e.g., laser scanned point clouds). We formulate multi-model fitting problem as a sequential decision making process. We then use a deep reinforcement learning algorithm to learn the optimal decisions towards the best fitting result. In this paper, we have compared our method against the state-of-the-art on simulated data. The results demonstrated that our approach significantly reduced the number of fitting iterations.