TechRxiv
submission.pdf (19.31 MB)
0/0

Mosaic Super-resolution via Sequential Feature Pyramid Networks

Download (19.31 MB)
preprint
posted on 30.12.2019 by Mehrdad Shoeiby, Mohammad Ali Armin, Sadegh Aliakbarian, Saeed Anwar, Lars petersson
Advances in the design of multi-spectral cameras have
led to great interests in a wide range of applications, from
astronomy to autonomous driving. However, such cameras
inherently suffer from a trade-off between the spatial and
spectral resolution. In this paper, we propose to address
this limitation by introducing a novel method to carry out
super-resolution on raw mosaic images, multi-spectral or
RGB Bayer, captured by modern real-time single-shot mo-
saic sensors. To this end, we design a deep super-resolution
architecture that benefits from a sequential feature pyramid
along the depth of the network. This, in fact, is achieved
by utilizing a convolutional LSTM (ConvLSTM) to learn the
inter-dependencies between features at different receptive
fields. Additionally, by investigating the effect of different
attention mechanisms in our framework, we show that a
ConvLSTM inspired module is able to provide superior at-
tention in our context. Our extensive experiments and anal-
yses evidence that our approach yields significant super-
resolution quality, outperforming current state-of-the-art
mosaic super-resolution methods on both Bayer and multi-
spectral images. Additionally, to the best of our knowledge,
our method is the first specialized method to super-resolve
mosaic images, whether it be multi-spectral or Bayer.

History

Email Address of Submitting Author

mehrdad.shoeiby@gmail.com

Submitting Author's Institution

CSIRO-DATA61

Submitting Author's Country

Australia

Licence

Exports

Licence

Exports