Learning Parallax Attention for Stereo Image Super-Resolution
arXiv:1903.05784
Abstract
Stereo image pairs can be used to improve the performance of super-resolution (SR) since additional information is provided from a second viewpoint. However, it is challenging to incorporate this information for SR since disparities between stereo images vary significantly. In this paper, we propose a parallax-attention stereo superresolution network (PASSRnet) to integrate the information from a stereo image pair for SR. Specifically, we introduce a parallax-attention mechanism with a global receptive field along the epipolar line to handle different stereo images with large disparity variations. We also propose a new and the largest dataset for stereo image SR (namely, Flickr1024). Extensive experiments demonstrate that the parallax-attention mechanism can capture correspondence between stereo images to improve SR performance with a small computational and memory cost. Comparative results show that our PASSRnet achieves the state-of-the-art performance on the Middlebury, KITTI 2012 and KITTI 2015 datasets.
To appear in CVPR 2019
References in corpus (8)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Multi-Task Learning as Multi-Objective Optimization
- End-to-End Learning of Geometry and Context for Deep Stereo Regression
- Non-Local Recurrent Network for Image Restoration
- Dual Attention Network for Scene Segmentation
- PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
- Fast and Accurate Single Image Super-Resolution via Information Distillation Network
- Left-Right Comparative Recurrent Model for Stereo Matching