Our framework consists of two parts: (a) A fine-grained kernel sparsity schema with a sparsity granularity between structured pruning and unstructured pruning.
Since the high resolution of intermediate features in SISR models increases memory and computational requirements, efficient SISR transformers are more favored.
We develop two simple yet effective plug and play methods to improve the performance of existing local and non-local propagation-based VSR algorithms on widely-used public videos.
Many Image Quality Assessment(IQA) algorithms have been designed to tackle this problem.
Moreover, we revisit the popular contrastive loss and observe that the selection of intermediate features of its feature extractor has great influence on the performance.
Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution.
The style modulation aims to generate realistic face details and the feature modulation dynamically fuses the multi-level encoded features and the generated ones conditioned on the upscaling factor.
Instead of estimating alignment information, we propose a simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) to effectively propagate and gather the information from unaligned neighboring frames for better video deblurring.
Ranked #11 on Deblurring on GoPro