Depth estimation from a single omnidirectional image using domain adaptation

Abstract

Omnidirectional cameras are becoming popular in various applications owing to their ability to capture the full surrounding scene in real-time. However, depth estimation for an omnidirectional scene is more difficult than normal perspective images due to its different system properties and distortions. It is hard to use normal depth estimation methods such as stereo matching or RGB-D sensing. A deep-learning-based single-shot depth estimation approach can be a good solution, but it requires a large labelled dataset for training. The 3D60 dataset, the largest omnidirectional dataset with depth labels, is not applicable for general scene depth estimation because it covers very limited scenes. In order to overcome this limitation, we propose a depth estimation architecture for a single omnidirectional image using domain adaptation. The proposed architecture gets labelled source domain and unlabelled target domain data together as its input and estimated depth information of the target domain using the Generative Adversarial Networks (GAN) based method. The proposed architecture shows >10% higher accuracy in depth estimation than traditional encoder-decoder models with a limited labelled dataset.

More information

Identifiers

ORCID for Yihong Wu: orcid.org/0000-0003-3340-2535

ORCID for Yuwen Heng: orcid.org/0000-0003-3793-4811

ORCID for Mahesan Niranjan: orcid.org/0000-0001-7021-140X

ORCID for Hansung Kim: orcid.org/0000-0003-4907-0491

Catalogue record

Export record

Altmetrics