-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yoo_2023_WACV, author = {Yoo, Jinsu and Kim, Taehoon and Lee, Sihaeng and Kim, Seung Hwan and Lee, Honglak and Kim, Tae Hyun}, title = {Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {4956-4965} }
Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution
Abstract
Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods. However, these approaches suffer from essential shortsightedness created by only utilizing the standard self-attention-based reasoning. In this paper, we introduce an effective hybrid SR network to aggregate enriched features, including local features from CNNs and long-range multi-scale dependencies captured by transformers. Specifically, our network comprises transformer and convolutional branches, which synergetically complement each representation during the restoration procedure. Furthermore, we propose a cross-scale token attention module, allowing the transformer branch to exploit the informative relationships among tokens across different scales efficiently. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
Related Material