Efficient Hybrid Feature Interaction Network for Stereo Image Super-Resolution

It is very challenging to fully use cross-view information for stereo image super-resolution. Previous methods using pixel-based parallax-attention mechanisms do not consider neighborhood pixels. Also, they typically use convolutions for basic feature extraction, which may not be as effective as modern self-attention mechanisms in transformers. To address these limitations, we propose an efficient hybrid feature interaction network for stereo image super-resolution. Specifically, we propose a shifted cross-view interaction block that integrates neighborhood pixels and imposes constraints on the disparity range during cross-view interactions. In addition, we propose a hybrid feature interaction block consisting of local and global interaction branches for extracting intra-view features efficiently. In this block, we propose a design that incorporates lightweight attention connections and a partial downsampling operation to enhance spatial and channel feature interaction with high efficiency. Additionally, a dilated efficient channel attention mechanism is proposed to obtain cross-channel interactions within features. Experimental results evaluated on various metrics (PSNR, SSIM, and LPIPS) demonstrate that the proposed method achieves state-of-the-art stereo image super-resolution performance at relatively low computational cost. Moreover, the super-resolution images obtained by the proposed method achieve the smallest stereo matching errors compared to other methods.