Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution
This work addresses a specific bottleneck in image super-resolution for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of shortsightedness in transformer-based super-resolution methods by introducing a hybrid network that aggregates local CNN features with long-range transformer dependencies, achieving state-of-the-art results on multiple benchmark datasets.
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.