Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution
This work addresses image super-resolution at arbitrary scales, which is useful for applications like medical imaging or digital media, though it appears incremental as it builds on existing implicit neural representation methods.
The paper tackles arbitrary-scale super-resolution by proposing a Local Implicit Transformer (LIT) that integrates attention mechanisms and frequency encoding, and a Cascaded LIT (CLIT) with multi-scale features and cumulative training. The results show that LIT and CLIT achieve favorable performance and outperform prior works in arbitrary super-resolution tasks.
Implicit neural representation has recently shown a promising ability in representing images with arbitrary resolutions. In this paper, we present a Local Implicit Transformer (LIT), which integrates the attention mechanism and frequency encoding technique into a local implicit image function. We design a cross-scale local attention block to effectively aggregate local features. To further improve representative power, we propose a Cascaded LIT (CLIT) that exploits multi-scale features, along with a cumulative training strategy that gradually increases the upsampling scales during training. We have conducted extensive experiments to validate the effectiveness of these components and analyze various training strategies. The qualitative and quantitative results demonstrate that LIT and CLIT achieve favorable results and outperform the prior works in arbitrary super-resolution tasks.