A Light Dual-Task Neural Network for Haze Removal

Publication Type:
Journal Article
IEEE Signal Processing Letters, 2018, 25 (8), pp. 1231 - 1235
Issue Date:
Filename Description Size
08392765.pdfPublished Version721.35 kB
Adobe PDF
Full metadata record
© 1994-2012 IEEE. Single-image dehazing is a challenging problem due to its ill-posed nature. Existing methods rely on a suboptimal two-step approach, where an intermediate product like a depth map is estimated, based on which the haze-free image is subsequently generated using an artificial prior formula. In this paper, we propose a light dual-task Neural Network called LDTNet that restores the haze-free image in one shot. We use transmission map estimation as an auxiliary task to assist the main task, haze removal, in feature extraction and to enhance the generalization of the network. In LDTNet, the haze-free image and the transmission map are produced simultaneously. As a result, the artificial prior is reduced to the smallest extent. Extensive experiments demonstrate that our algorithm achieves superior performance against the state-of-the-art methods on both synthetic and real-world images.
Please use this identifier to cite or link to this item: