University of Surrey

Test tubes in the lab Research in the ATI Dance Research

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

Spencer, Jaime, Bowden, Richard and Hadfield, Simon (2020) DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning In: CVPR 2020, 2020-06-14-2020-06-19, Seattle, Washington.

[img] Text
[CVPR 2020] Submission#10060_ DeFeat-Net_ General Monocular Depth via Simultaneous Unsupervised Representation Learning.eml - Accepted version Manuscript

Download (4kB)


In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging domains such as nighttime scenes or adverse weather conditions where assumptions about photometric consistency break down. We propose DeFeat-Net (Depth & Feature network), an approach to simultaneously learn a cross-domain dense feature representation, alongside a robust depth-estimation framework based on warped feature consistency. The resulting feature representation is learned in an unsupervised manner with no explicit ground-truth correspondences required. We show that within a single domain, our technique is comparable to both the current state of the art in monocular depth estimation and supervised feature representation learning. However, by simultaneously learning features, depth and motion, our technique is able to generalize to challenging domains, allowing DeFeat-Net to outperform the current state-of-the-art with around 10% reduction in all error measures on more challenging sequences such as nighttime driving.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
Date : 26 February 2020
Funders : EPSRC - Engineering and Physical Sciences Research Council
Copyright Disclaimer : © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Additional Information : Paper ID - 10060 This work was partially funded by the EPSRC under grant agreements (EP/R512217/1, EP/S016317/1 and EP/S035761/1). We would also like to thank NVIDIA Corporation for their Titan Xp GPU grant.
Depositing User : Diane Maxfield
Date Deposited : 21 Apr 2020 16:25
Last Modified : 16 Jun 2020 02:08

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800