UnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation

V. Madhu Babu, Kaushik Das, Anima Majumdar, Swagat Kumar

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

35 Citations (Scopus)


This paper presents an unsupervised deep learning framework called UnDEMoN for estimating dense depth map and 6-DoF camera pose information directly from monocular images. The proposed network is trained using unlabeled monocular stereo image pairs and is shown to provide superior performance in depth and ego-motion estimation compared to the existing state-of-the-art. These improvements are achieved by introducing a new objective function that aims to minimize spatial as well as temporal reconstruction losses simultaneously. These losses are defined using bi-linear sampling kernel and penalized using the Charbonnier penalty function. The objective function, thus created, provides robustness to image gradient noises thereby improving the overall estimation accuracy without resorting to any coarse to fine strategies which are currently prevalent in the literature. Another novelty lies in the fact that we combine a disparity-based depth estimation network with a pose estimation network to obtain absolute scale-aware 6 DOF Camera pose and superior depth map. The effectiveness of the proposed approach is demonstrated through performance comparison with the existing supervised and unsupervised methods on the KITTI driving dataset.
Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages7
ISBN (Print)9781538680940
Publication statusPublished - 27 Dec 2018

Publication series

NameIEEE International Conference on Intelligent Robots and Systems


Dive into the research topics of 'UnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation'. Together they form a unique fingerprint.

Cite this