Group Feature Information Distillation Network For Single Image Super-resolution

Chen, Ming Zhuo; Wu, Jun

doi:10.1109/iccc54389.2021.9674256

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distillation in the feature domain has the advantage of being capable of non-linear conversion on both sides of several tens of channels [25], while the information on the final output image is only 3 channels and one side is fixed. Moreover, the output end of the feature is fixed to converge to the HR image, resulting in stable information without divergence.…”

Section: (4)mentioning

confidence: 99%

Dual-Stage Super-Resolution for Edge Devices

Park,

Choi,

Park

et al. 2023

IEEE Access

View full text Add to dashboard Cite

To reduce memory usage, edge devices such as TVs use super-resolution(SR) with dedicated hardware networks. Dedicated hardware has the disadvantage of being difficult to change and difficult to improve performance. We propose a dual-structured SR system that can extend this dedicated hardware, suggesting a way to improve the restoration performance for compression with minimal change in hardware. Edge devices such as general TVs deal with moving videos rather than still images. In this case, the video includes video compression, and a preprocessing step of restoring deterioration is useful. We propose as the main idea that these steps can be handled while removing only pixel shuffle layers from existing networks. Our proposed SR method consists of two stages: 1) restoring from the video compression without changing the size of LR images and 2) increasing the resolution. The first stage can be learned by reducing the difference between video-LR (Low-Resolution video images with codec degradation) and downscaled-HR (video images made without codec degradation by simply reducing the size of High-Resolution video). The second stage, resolution enhancement, performs the same task as the traditional SISR task, except that it focuses on restoring the output of the first stage rather than a downscaled-HR. Our new dataset for this processing, HD2UHD, consists of (video-LR, downscaled-HR, and HR) tuples. We also propose a new scheme of input distillation that utilizes video-LR and downscaled-HR at the same time.

show abstract

Section: (4)mentioning

confidence: 99%