Cascaded Deep Networks with Multiple Receptive Fields for Infrared Image Super-Resolution

Zewei He, Siliang Tang, Jiangxin Yang, Yanlong Cao (Corresponding Author), Michael Ying Yang, Yanpeng Cao

Research output: Contribution to journalArticleAcademicpeer-review

10 Citations (Scopus)


Infrared images have a wide range of military and civilian applications including night vision, surveillance and robotics. However, high-resolution infrared detectors are difficult to fabricate and their manufacturing cost is expensive. In this work, we present a cascaded architecture of deep neural networks with multiple receptive fields to increase the spatial resolution of infrared images by a large scale factor (×8). Instead of reconstructing a high-resolution image from its low-resolution version using a single complex deep network, the key idea of our approach is to set up a mid-point (scale ×2) between scale ×1 and ×8 such that lost information can be divided into two components. Lost information within each component contains similar patterns thus can be more accurately recovered even using a simpler deep network. In our proposed cascaded architecture, two consecutive deep networks with different receptive fields are jointly trained through a multi-scale loss function. The first network with a large receptive field is applied to recover large-scale structure information, while the second one uses a relatively smaller receptive field to reconstruct small-scale image details. Our proposed method is systematically evaluated using realistic infrared images. Compared with state-of-theart Super-Resolution methods, our proposed cascaded approach achieves improved reconstruction accuracy using significantly less parameters.
Original languageEnglish
Article number8432397
Number of pages13
JournalIEEE transactions on circuits and systems for video technology
Publication statusAccepted/In press - 10 Aug 2018



Fingerprint Dive into the research topics of 'Cascaded Deep Networks with Multiple Receptive Fields for Infrared Image Super-Resolution'. Together they form a unique fingerprint.

Cite this