Cross-view Aggregation Network For Stereo Image Super-Resolution

Zhitao Chen, Tao Lu, Kanghui Zhao, Bolin Zhu, Zhen Li, Jiaming Wang, Yanduo Zhang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 6469-6478

Although stereo image super-resolution has been extensively studied many existing works only rely on attention in a single epipolar direction to reconstruct stereo images. In the case of asymmetric parallax images these methods often struggle to capture reliable stereo correspondence resulting in reconstructed images suffering from blurring and artifacts. In this paper we propose a novel method called Cross-View Aggregation Network for Stereo Image Super-Resolution (CANSSR) and explore the relationship between multi-directional epipolar lines to construct reliable stereo correspondence. Specifically we propose a multi-directional cross-view aggregation module (MCAM) that effectively captures multi-directional stereo correspondence and obtains cross-view complementary information. Furthermore we design a channel-spatial aggregation module (CSAM) that aggregates multi-order global-local information in intra-view to reconstruct clearer texture features. In addition we equip a large kernel convolution in the Feed-forward Network to acquire richer detailed texture information. The extensive experiments conclusively demonstrate that CANSSR outperforms the state-of-the-art method both qualitatively and quantitatively in terms of stereo image super-resolution on the Flickr 1024 and Middlebury datasets.