Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution
Keywords:Low Level & Physics-based Vision
AbstractTraditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. In this paper, we propose a Omni-frequency Region-adaptive Network (OR-Net) to address both challenges, here we call features of all low, middle and high frequencies omni-frequency features. Specifically, we start from the frequency perspective and design a Frequency Decomposition (FD) module to separate different frequency components to comprehensively compensate the information lost for real LR image. Then, considering the different regions of real LR image have different frequency information lost, we further design a Region-adaptive Frequency Aggregation (RFA) module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions. The extensive experiments endorse the high-efficient, effective, and scenario-agnostic nature of our OR-Net for RealSR.
How to Cite
Li, X., Jin, X., Yu, T., Sun, S., Pang, Y., Zhang, Z., & Chen, Z. (2021). Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 1975-1983. https://doi.org/10.1609/aaai.v35i3.16293
AAAI Technical Track on Computer Vision II