Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution

TL;DR

This paper introduces HTCAN, a hybrid transformer and CNN network for stereo image super-resolution, effectively leveraging stereo information and advanced training strategies to outperform existing methods.

Contribution

The paper proposes a novel hybrid network combining transformers and CNNs for stereo super-resolution, addressing limitations of existing transformer-based methods.

Findings

Achieved 23.90dB PSNR in NTIRE 2023 challenge

Outperformed existing stereo super-resolution methods

Utilized multi-patch training and larger window sizes

Abstract

Multi-stage strategies are frequently employed in image restoration tasks. While transformer-based methods have exhibited high efficiency in single-image super-resolution tasks, they have not yet shown significant advantages over CNN-based methods in stereo super-resolution tasks. This can be attributed to two key factors: first, current single-image super-resolution transformers are unable to leverage the complementary stereo information during the process; second, the performance of transformers is typically reliant on sufficient data, which is absent in common stereo-image super-resolution algorithms. To address these issues, we propose a Hybrid Transformer and CNN Attention Network (HTCAN), which utilizes a transformer-based network for single-image enhancement and a CNN-based network for stereo information fusion. Furthermore, we employ a multi-patch training strategy and larger window sizes to activate more input pixels for super-resolution. We also revisit other advanced techniques, such as data augmentation, data ensemble, and model ensemble to reduce overfitting and data bias. Finally, our approach achieved a score of 23.90dB and emerged as the winner in Track 1 of the NTIRE 2023 Stereo Image Super-Resolution Challenge.