Atapour-Abarghouei, A. and Breckon, T.P. (2018) 'Real-time monocular depth estimation using synthetic data with domain adaptation via image style transfer.', in Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), 18-22 June 2018, Salt Lake City, Utah. Piscataway, NJ: IEEE, pp. 2800-2810.
Monocular depth estimation using learning-based approaches has become promising in recent years. However, most monocular depth estimators either need to rely on large quantities of ground truth depth data, which is extremely expensive and difficult to obtain, or predict disparity as an intermediary step using a secondary supervisory signal leading to blurring and other artefacts. Training a depth estimation model using pixel-perfect synthetic data can resolve most of these issues but introduces the problem of domain bias. This is the inability to apply a model trained on synthetic data to real-world scenarios. With advances in image style transfer and its connections with domain adaptation (Maximum Mean Discrepancy), we take advantage of style transfer and adversarial training to predict pixel perfect depth from a single real-world color image based on training over a large corpus of synthetic environment data. Experimental results indicate the efficacy of our approach compared to contemporary state-of-the-art techniques.
|Item Type:||Book chapter|
|Keywords:||Monocular depth, Generative adversarial network, GAN, Depth map, Disparity, Depth from single image|
|Full text:||(AM) Accepted Manuscript|
Download PDF (4070Kb)
|Publisher Web site:||https://doi.org/10.1109/CVPR.2018.00296|
|Publisher statement:||© 2018 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.|
|Date accepted:||19 February 2018|
|Date deposited:||20 March 2018|
|Date of first online publication:||17 December 2018|
|Date first made open access:||29 November 2021|
Save or Share this output
|Look up in GoogleScholar|