Deep self-guided cost aggregation for stereo matching

In this paper, we present a deep self-guided cost aggregation method used to obtain an accurate disparity map from a pair of stereo images. Conventional cost aggregation methods typically perform joint image filtering on each cost volume slice. Thus, a guidance image is necessary for the conventional methods to work effectively. However, a guidance image might be unreliable due to several distortions, such as noise, blur, radiometric variation. Based on our observations, each cost volume slice can guide itself based on the internal features. However, finding a direct mapping function from the initial and filtered cost volume slice without any guidance image is difficult. To solve this problem, we use an advanced deep learning technique to perform self-guided cost aggregation. Because of the absence of ground truth cost volume, we offer the solution for the dataset generation. Our proposed deep learning network consists of two sub-networks: dynamic weight network and descending filtering network. We integrate the feature reconstruction loss and the pixelwise mean square loss function to preserve the edge property. Experimental results show that the proposed method achieves better results even though it does not employ a guidance image.