A Front-End for Dense Monocular SLAM using a Learned Outlier Mask Prior

TL;DR

This paper introduces a dense CNN-assisted SLAM front-end that leverages a learned outlier mask prior to enhance tracking robustness, combining deep learning with classical SLAM for improved dense mapping.

Contribution

It proposes using the CNN-derived outlier mask as a prior in a classical SLAM framework, enabling dense, outlier-resistant tracking and fusion.

Findings

Improved robustness in SLAM tracking using the outlier mask prior.

Implementation of a dense CNN-assisted SLAM front-end in TensorFlow.

Evaluation on indoor and outdoor datasets demonstrating effectiveness.

Abstract

Recent achievements in depth prediction from a single RGB image have powered the new research area of combining convolutional neural networks (CNNs) with classical simultaneous localization and mapping (SLAM) algorithms. The depth prediction from a CNN provides a reasonable initial point in the optimization process in the traditional SLAM algorithms, while the SLAM algorithms further improve the CNN prediction online. However, most of the current CNN-SLAM approaches have only taken advantage of the depth prediction but not yet other products from a CNN. In this work, we explore the use of the outlier mask, a by-product from unsupervised learning of depth from video, as a prior in a classical probability model for depth estimate fusion to step up the outlier-resistant tracking performance of a SLAM front-end. On the other hand, some of the previous CNN-SLAM work builds on feature-based sparse SLAM methods, wasting the per-pixel dense prediction from a CNN. In contrast to these sparse methods, we devise a dense CNN-assisted SLAM front-end that is implementable with TensorFlow and evaluate it on both indoor and outdoor datasets.