F[formula omitted]Depth: Self-supervised indoor monocular depth estimation via optical flow consistency and feature map synthesis.

Self-supervised monocular depth estimation methods have been increasingly given much attention due to the benefit of not requiring large, labelled datasets. Such self-supervised methods require high-quality salient features and consequently suffer from severe performance drop for indoor scenes, where low-textured regions dominant in the scenes are almost indiscriminative. To address the issue, we propose a self-supervised indoor monocular depth estimation framework called F 2 Depth. A self-supervised optical flow estimation network is introduced to supervise depth learning. To improve optical flow estimation performance in low-textured areas, only some patches of points with more discriminative features are adopted for finetuning based on our well-designed patch-based photometric loss. The finetuned optical flow estimation network generates high-accuracy optical flow as a supervisory signal for depth estimation. Correspondingly, an optical flow consistency loss is designed. Multi-scale feature maps produced by finetuned optical flow estimation network perform warping to compute feature map synthesis loss as another supervisory signal for depth learning. Experimental results on the NYU Depth V2 dataset demonstrate the effectiveness of the framework and our proposed losses. To evaluate the generalization ability of our F 2 Depth, we collect a Campus Indoor depth dataset composed of approximately 1500 points selected from 99 images in 18 scenes. Zero-shot generalization experiments on 7-Scenes dataset and Campus Indoor achieve δ 1 accuracy of 75.8% and 76.0% respectively. The accuracy results show that our model can generalize well to monocular images captured in unknown indoor scenes. [Display omitted] • A self-supervised indoor monocular depth estimation framework F 2 Depth is proposed. • A patch-based photometric loss for the optical flow estimation network is designed. • A multi-scale feature map synthesis loss for depth estimation is designed. • An optical flow consistency loss for depth estimation is designed. • A Campus Indoor dataset is collected to perform zero-shot generalization experiment. [ABSTRACT FROM AUTHOR]

Copyright of Engineering Applications of Artificial Intelligence is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)