Recently, the performance of super-resolution has been improved by the stereo images since the additional information could be obtained from another view. However, it is a challenge to interact the cross-view information since disparities between left and right images are variable. To address this issue, we propose a disparity feature alignment module (DFAM) to exploit the disparity information for feature alignment and fusion. Specifically, we design a modified atrous spatial pyramid pooling module to estimate disparities and warp stereo features. Then we use spatial and channel attention for feature fusion. In addition, DFAM can be plugged into an arbitrary SISR network to super-resolve a stereo image pair. Extensive experiments demonstrate that DFAM incorporates stereo information with less inference time and memory cost. Moreover, RCAN equipped with DFAMs achieves better performance against state-of-the-art methods. The code can be obtained at https://github.com/JiawangDan/DFAM.

中文翻译：

---

立体图像超分辨率的视差特征对齐模块


最近，立体图像提高了超分辨率的性能，因为可以从另一个视图获得附加信息。然而，由于左右图像之间的差异是可变的，因此交互跨视图信息是一个挑战。为了解决这个问题，我们提出了一个视差特征对齐模块（DFAM）来利用视差信息进行特征对齐和融合。具体来说，我们设计了一个改进的多孔空间金字塔池模块来估计视差和扭曲立体特征。然后我们使用空间和通道注意力进行特征融合。此外，DFAM 可以插入任意 SISR 网络以超分辨率立体图像对。大量实验表明，DFAM 结合了立体信息，并且推理时间和内存成本更少。此外，配备 DFAM 的 RCAN 比最先进的方法取得了更好的性能。代码可以在https://github.com/JiawangDan/DFAM获取。