Mosaic Super-Resolution via Sequential Feature Pyramid Networks

Mehrdad Shoeiby, Ali Armin, Sadegh Aliakbarian, Saeed Anwar, Lars Petersson; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 84-85

Abstract


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 mosaic 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 attention in our context. Our extensive experiments and analyses 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.

Related Material


[pdf]
[bibtex]
@InProceedings{Shoeiby_2020_CVPR_Workshops,
author = {Shoeiby, Mehrdad and Armin, Ali and Aliakbarian, Sadegh and Anwar, Saeed and Petersson, Lars},
title = {Mosaic Super-Resolution via Sequential Feature Pyramid Networks},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}