Accurate Multi-image Super-Resolution Using Deep Residual Networks
In person: 11 October 2021 • 13:00 - 14:30 China Standard Time
We propose a multi-frame low-resolution (LR) images input super-resolution(SR) network(MFSRResNet) based on convolutional neural networks(CNNs) and residual learning. MFSRResNet trains on DIV2K800 and test on benchmark datasets for different upscaling factors ×2, ×3, ×4 and× 8.We train MFSRResNet with five-frame LR images inputs .there are different sub-pixel shifts among input LR images. Extensive experimental results demonstrate that MFSRResNet with five-frame LR images input shows significant performance improvement both in accuracy and visual quality compared to current state-of-the-art SISR methods. Our method MFSRResNet proves the advantage of multi-frame input as for SR task, especially meaningful for large upscaling factor such as ×8,×16.
Beijing Institute of Technology (China)