Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution

Salma Abdel Magid, Yulun Zhang, Donglai Wei, Won-Dong Jang, Zudi Lin, Yun Fu, Hanspeter Pfister; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 4288-4297

Abstract


Deep convolutional neural networks (CNNs) have pushed forward the frontier of super-resolution (SR) research. However, current CNN models exhibit a major flaw: they are biased towards learning low-frequency signals. This bias becomes more problematic for the image SR task which targets reconstructing all fine details and image textures. To tackle this challenge, we propose to improve the learning of high-frequency features both locally and globally and introduce two novel architectural units to existing SR models. Specifically, we propose a dynamic high-pass filtering (HPF) module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals. We also propose a matrix multi-spectral channel attention (MMCA) module that predicts the attention map of features decomposed in the frequency domain. This module operates in a global context to adaptively recalibrate feature responses at different frequencies. Extensive qualitative and quantitative results demonstrate that our proposed modules achieve better accuracy and visual improvements against state-of-the-art methods on several benchmark datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Magid_2021_ICCV, author = {Magid, Salma Abdel and Zhang, Yulun and Wei, Donglai and Jang, Won-Dong and Lin, Zudi and Fu, Yun and Pfister, Hanspeter}, title = {Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {4288-4297} }