Image Super-Resolution using Efficient Striped Window Transformer
This work addresses the problem of efficient super-resolution for applications requiring lightweight models, though it is incremental in improving transformer-based methods.
The paper tackles the challenge of balancing performance and complexity in lightweight image super-resolution by proposing an Efficient Striped Window Transformer, which outperforms state-of-the-art methods with fewer parameters, faster inference, smaller FLOPs, and less memory consumption.
Transformers have achieved remarkable results in single-image super-resolution (SR). However, the challenge of balancing model performance and complexity has hindered their application in lightweight SR (LSR). To tackle this challenge, we propose an efficient striped window transformer (ESWT). We revisit the normalization layer in the transformer and design a concise and efficient transformer structure to build the ESWT. Furthermore, we introduce a striped window mechanism to model long-term dependencies more efficiently. To fully exploit the potential of the ESWT, we propose a novel flexible window training strategy that can improve the performance of the ESWT without additional cost. Extensive experiments show that ESWT outperforms state-of-the-art LSR transformers, and achieves a better trade-off between model performance and complexity. The ESWT requires fewer parameters, incurs faster inference, smaller FLOPs, and less memory consumption, making it a promising solution for LSR.